AI/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-09-20 00:07:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #4660 from oobabooga/dev

Browse Source 
Merge dev branch
This commit is contained in:
oobabooga 2023-11-19 13:32:08 -03:00 committed by GitHub
commit d1bba48a83
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
42 changed files with 529 additions and 244 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -169,7 +169,7 @@ cp docker/.env.example .env
docker compose up --build docker compose up --build
``` ```
* You need to have docker compose v2.17 or higher installed. See [this guide](https://github.com/oobabooga/text-generation-webui/wiki/09-%E2%80%90-Docker) for instructions. * You need to have Docker Compose v2.17 or higher installed. See [this guide](https://github.com/oobabooga/text-generation-webui/wiki/09-%E2%80%90-Docker) for instructions.
* For additional docker files, check out [this repository](https://github.com/Atinoda/text-generation-webui-docker). * For additional docker files, check out [this repository](https://github.com/Atinoda/text-generation-webui-docker).
### Updating the requirements ### Updating the requirements
@ -325,7 +325,6 @@ Optionally, you can use the following command-line flags:
| `--mlock` | Force the system to keep the model in RAM. | | `--mlock` | Force the system to keep the model in RAM. |
| `--n-gpu-layers N_GPU_LAYERS` | Number of layers to offload to the GPU. | | `--n-gpu-layers N_GPU_LAYERS` | Number of layers to offload to the GPU. |
| `--tensor_split TENSOR_SPLIT` | Split the model across multiple GPUs. Comma-separated list of proportions. Example: 18,17. | | `--tensor_split TENSOR_SPLIT` | Split the model across multiple GPUs. Comma-separated list of proportions. Example: 18,17. |
| `--llama_cpp_seed SEED` | Seed for llama-cpp models. Default is 0 (random). |
| `--numa` | Activate NUMA task allocation for llama.cpp. | | `--numa` | Activate NUMA task allocation for llama.cpp. |
| `--logits_all`| Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower. | | `--logits_all`| Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower. |
| `--cache-capacity CACHE_CAPACITY` | Maximum cache capacity (llama-cpp-python). Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed. | | `--cache-capacity CACHE_CAPACITY` | Maximum cache capacity (llama-cpp-python). Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed. |
@ -414,6 +413,8 @@ Optionally, you can use the following command-line flags:
| `--public-api-id PUBLIC_API_ID` | Tunnel ID for named Cloudflare Tunnel. Use together with public-api option. | | `--public-api-id PUBLIC_API_ID` | Tunnel ID for named Cloudflare Tunnel. Use together with public-api option. |
| `--api-port API_PORT` | The listening port for the API. | | `--api-port API_PORT` | The listening port for the API. |
| `--api-key API_KEY` | API authentication key. | | `--api-key API_KEY` | API authentication key. |
| `--admin-key ADMIN_KEY` | API authentication key for admin tasks like loading and unloading models. If not set, will be the same as --api-key. |
| `--nowebui` | Do not launch the Gradio UI. Useful for launching the API in standalone mode. |
#### Multimodal #### Multimodal

20
css/main.css
View File

@ -648,3 +648,23 @@ div.svelte-362y77>*, div.svelte-362y77>.form>* {
.options { .options {
z-index: 100 !important; z-index: 100 !important;
} }
/* ----------------------------------------------
Big profile picture for characters
---------------------------------------------- */
.bigProfilePicture {
position: fixed;
bottom: 0;
left: 0;
width: calc((100vw - 880px - 120px) /2);
}
.pfp_character:hover {
cursor: pointer;
}
@media screen and (width <= 1300px) {
.bigProfilePicture {
display: none;
}
}

1
docker/.dockerignore
View File

@ -5,5 +5,4 @@ Dockerfile
/models /models
/presets /presets
/prompts /prompts
/softprompts
/training /training

14
docker/.env.example
View File

@ -3,13 +3,8 @@
# https://developer.nvidia.com/cuda-gpus you can find the version for your card here # https://developer.nvidia.com/cuda-gpus you can find the version for your card here
TORCH_CUDA_ARCH_LIST=7.5 TORCH_CUDA_ARCH_LIST=7.5
# these commands worked for me with roughly 4.5GB of vram # your command-line flags go here:
CLI_ARGS=--model llama-7b-4bit --wbits 4 --listen --auto-devices CLI_ARGS=
# the following examples have been tested with the files linked in docs/README_docker.md:
# example running 13b with 4bit/128 groupsize : CLI_ARGS=--model llama-13b-4bit-128g --wbits 4 --listen --groupsize 128 --pre_layer 25
# example with loading api extension and public share: CLI_ARGS=--model llama-7b-4bit --wbits 4 --listen --auto-devices --no-stream --extensions api --share
# example running 7b with 8bit groupsize : CLI_ARGS=--model llama-7b --load-in-8bit --listen --auto-devices
# the port the webui binds to on the host # the port the webui binds to on the host
HOST_PORT=7860 HOST_PORT=7860
@ -21,10 +16,5 @@ HOST_API_PORT=5000
# the port the api binds to inside the container # the port the api binds to inside the container
CONTAINER_API_PORT=5000 CONTAINER_API_PORT=5000
# the port the api stream endpoint binds to on the host
HOST_API_STREAM_PORT=5005
# the port the api stream endpoint binds to inside the container
CONTAINER_API_STREAM_PORT=5005
# the version used to install text-generation-webui from # the version used to install text-generation-webui from
WEBUI_VERSION=HEAD WEBUI_VERSION=HEAD

2
docker/Dockerfile
View File

@ -73,5 +73,5 @@ RUN --mount=type=cache,target=/root/.cache/pip,rw \
ENV CLI_ARGS="" ENV CLI_ARGS=""
EXPOSE ${CONTAINER_PORT:-7860} ${CONTAINER_API_PORT:-5000} ${CONTAINER_API_STREAM_PORT:-5005} EXPOSE ${CONTAINER_PORT:-7860} ${CONTAINER_API_PORT:-5000}
CMD . /app/venv/bin/activate && python3 server.py ${CLI_ARGS} CMD . /app/venv/bin/activate && python3 server.py ${CLI_ARGS}

1
docker/docker-compose.yml
View File

@ -11,7 +11,6 @@ services:
ports: ports:
- "${HOST_PORT:-7860}:${CONTAINER_PORT:-7860}" - "${HOST_PORT:-7860}:${CONTAINER_PORT:-7860}"
- "${HOST_API_PORT:-5000}:${CONTAINER_API_PORT:-5000}" - "${HOST_API_PORT:-5000}:${CONTAINER_API_PORT:-5000}"
- "${HOST_API_STREAM_PORT:-5005}:${CONTAINER_API_STREAM_PORT:-5005}"
stdin_open: true stdin_open: true
tty: true tty: true
volumes: volumes:

8
docs/03 - Parameters Tab.md
View File

@ -11,9 +11,13 @@ LLMs work by generating one token at a time. Given your prompt, the model calcul
### Preset menu ### Preset menu
Can be used to save combinations of parameters for reuse. Can be used to save and load combinations of parameters for reuse.
The built-in presets were not manually chosen. They were obtained after a blind contest called "Preset Arena" where hundreds of people voted. The full results can be found [here](https://github.com/oobabooga/oobabooga.github.io/blob/main/arena/results.md). * **🎲 button**: creates a random yet interpretable preset. Only 1 parameter of each category is included for the categories: removing tail tokens, avoiding repetition, and flattening the distribution. That is, top_p and top_k are not mixed, and neither are repetition_penalty and frequency_penalty. You can use this button to break out of a loop of bad generations after multiple "Regenerate" attempts.
#### Built-in presets
These were obtained after a blind contest called "Preset Arena" where hundreds of people voted. The full results can be found [here](https://github.com/oobabooga/oobabooga.github.io/blob/main/arena/results.md).
A key takeaway is that the best presets are: A key takeaway is that the best presets are:

18
docs/09 - Docker.md
View File

@ -1,13 +1,21 @@
Docker Compose is a way of installing and launching the web UI in an isolated Ubuntu image using only a few commands. Docker Compose is a way of installing and launching the web UI in an isolated Ubuntu image using only a few commands.
In order to create the image as described in the main README, you must have docker compose 2.17 or higher: ## Installing Docker Compose
In order to create the image as described in the main README, you must have Docker Compose installed (2.17 or higher is recommended):
``` ```
~$ docker compose version ~$ docker compose version
Docker Compose version v2.17.2 Docker Compose version v2.21.0
``` ```
Make sure to also create the necessary symbolic links: The installation instructions for various Linux distributions can be found here:
https://docs.docker.com/engine/install/ubuntu/#install-using-the-repository
## Launching the image
Use these commands to launch the image:
``` ```
cd text-generation-webui cd text-generation-webui
@ -17,13 +25,11 @@ cp docker/.env.example .env
docker compose up --build docker compose up --build
``` ```
## Table of contents ## More detailed installation instructions
* [Docker Compose installation instructions](#docker-compose-installation-instructions) * [Docker Compose installation instructions](#docker-compose-installation-instructions)
* [Repository with additional Docker files](#dedicated-docker-repository) * [Repository with additional Docker files](#dedicated-docker-repository)
## Docker Compose installation instructions
By [@loeken](https://github.com/loeken). By [@loeken](https://github.com/loeken).
- [Ubuntu 22.04](#ubuntu-2204) - [Ubuntu 22.04](#ubuntu-2204)

23
docs/12 - OpenAI API.md
View File

@ -97,6 +97,29 @@ curl http://127.0.0.1:5000/v1/chat/completions \
}' }'
``` ```
#### Logits
```
curl -k http://127.0.0.1:5000/v1/internal/logits \
-H "Content-Type: application/json" \
-d '{
"prompt": "Who is best, Asuka or Rei? Answer:",
"use_samplers": false
}'
```
#### Logits after sampling parameters
```
curl -k http://127.0.0.1:5000/v1/internal/logits \
-H "Content-Type: application/json" \
-d '{
"prompt": "Who is best, Asuka or Rei? Answer:",
"use_samplers": true,
"top_k": 3
}'
```
#### Python chat example #### Python chat example
```python ```python

6
docs/What Works.md
View File

@ -2,13 +2,13 @@
| Loader | Loading 1 LoRA | Loading 2 or more LoRAs | Training LoRAs | Multimodal extension | Perplexity evaluation | | Loader | Loading 1 LoRA | Loading 2 or more LoRAs | Training LoRAs | Multimodal extension | Perplexity evaluation |
|----------------|----------------|-------------------------|----------------|----------------------|-----------------------| |----------------|----------------|-------------------------|----------------|----------------------|-----------------------|
| Transformers | ✅ | ✅ | ✅* | ✅ | ✅ | | Transformers | ✅ | ✅*** | ✅* | ✅ | ✅ |
| ExLlama_HF | ✅ | ❌ | ❌ | ❌ | ✅ | | ExLlama_HF | ✅ | ❌ | ❌ | ❌ | ✅ |
| ExLlamav2_HF | ✅ | ✅ | ❌ | ❌ | ✅ | | ExLlamav2_HF | ✅ | ✅ | ❌ | ❌ | ✅ |
| ExLlama | ✅ | ❌ | ❌ | ❌ | use ExLlama_HF | | ExLlama | ✅ | ❌ | ❌ | ❌ | use ExLlama_HF |
| ExLlamav2 | ✅ | ✅ | ❌ | ❌ | use ExLlamav2_HF | | ExLlamav2 | ✅ | ✅ | ❌ | ❌ | use ExLlamav2_HF |
| AutoGPTQ | ✅ | ❌ | ❌ | ✅ | ✅ | | AutoGPTQ | ✅ | ❌ | ❌ | ✅ | ✅ |
| GPTQ-for-LLaMa | ✅** | ✅ | ✅ | ✅ | ✅ | | GPTQ-for-LLaMa | ✅** | ✅*** | ✅ | ✅ | ✅ |
| llama.cpp | ❌ | ❌ | ❌ | ❌ | use llamacpp_HF | | llama.cpp | ❌ | ❌ | ❌ | ❌ | use llamacpp_HF |
| llamacpp_HF | ❌ | ❌ | ❌ | ❌ | ✅ | | llamacpp_HF | ❌ | ❌ | ❌ | ❌ | ✅ |
| ctransformers | ❌ | ❌ | ❌ | ❌ | ❌ | | ctransformers | ❌ | ❌ | ❌ | ❌ | ❌ |
@ -21,3 +21,5 @@
\* Training LoRAs with GPTQ models also works with the Transformers loader. Make sure to check "auto-devices" and "disable_exllama" before loading the model. \* Training LoRAs with GPTQ models also works with the Transformers loader. Make sure to check "auto-devices" and "disable_exllama" before loading the model.
\*\* Requires the monkey-patch. The instructions can be found [here](https://github.com/oobabooga/text-generation-webui/wiki/08-%E2%80%90-Additional-Tips#using-loras-with-gptq-for-llama). \*\* Requires the monkey-patch. The instructions can be found [here](https://github.com/oobabooga/text-generation-webui/wiki/08-%E2%80%90-Additional-Tips#using-loras-with-gptq-for-llama).
\*\*\* Multi-LoRA in PEFT is tricky and the current implementation does not work reliably in all cases.

14
extensions/gallery/script.py
View File

@ -91,11 +91,13 @@ def ui():
with gr.Accordion("Character gallery", open=False, elem_id='gallery-extension'): with gr.Accordion("Character gallery", open=False, elem_id='gallery-extension'):
update = gr.Button("Refresh") update = gr.Button("Refresh")
gr.HTML(value="<style>" + generate_css() + "</style>") gr.HTML(value="<style>" + generate_css() + "</style>")
gallery = gr.Dataset(components=[gr.HTML(visible=False)], gallery = gr.Dataset(
label="", components=[gr.HTML(visible=False)],
samples=generate_html(), label="",
elem_classes=["character-gallery"], samples=generate_html(),
samples_per_page=50 elem_classes=["character-gallery"],
) samples_per_page=50
)
update.click(generate_html, [], gallery) update.click(generate_html, [], gallery)
gallery.select(select_character, None, gradio['character_menu']) gallery.select(select_character, None, gradio['character_menu'])

3
extensions/openai/completions.py
View File

@ -203,6 +203,7 @@ def chat_completions_common(body: dict, is_legacy: bool = False, stream=False) -
turn_template = body['turn_template'] or turn_template turn_template = body['turn_template'] or turn_template
context_instruct = body['context_instruct'] or context_instruct context_instruct = body['context_instruct'] or context_instruct
system_message = body['system_message'] or system_message system_message = body['system_message'] or system_message
chat_instruct_command = body['chat_instruct_command'] or shared.settings['chat-instruct_command']
# Chat character # Chat character
character = body['character'] or shared.settings['character'] character = body['character'] or shared.settings['character']
@ -228,7 +229,7 @@ def chat_completions_common(body: dict, is_legacy: bool = False, stream=False) -
'system_message': system_message, 'system_message': system_message,
'custom_system_message': custom_system_message, 'custom_system_message': custom_system_message,
'turn_template': turn_template, 'turn_template': turn_template,
'chat-instruct_command': body['chat_instruct_command'], 'chat-instruct_command': chat_instruct_command,
'history': history, 'history': history,
'stream': stream 'stream': stream
}) })

8
extensions/openai/embeddings.py
View File

@ -1,6 +1,7 @@
import os import os
import numpy as np import numpy as np
from transformers import AutoModel
from extensions.openai.errors import ServiceUnavailableError from extensions.openai.errors import ServiceUnavailableError
from extensions.openai.utils import debug_msg, float_list_to_base64 from extensions.openai.utils import debug_msg, float_list_to_base64
@ -41,7 +42,12 @@ def load_embedding_model(model: str):
global embeddings_device, embeddings_model global embeddings_device, embeddings_model
try: try:
print(f"Try embedding model: {model} on {embeddings_device}") print(f"Try embedding model: {model} on {embeddings_device}")
embeddings_model = SentenceTransformer(model, device=embeddings_device) if 'jina-embeddings' in model:
embeddings_model = AutoModel.from_pretrained(model, trust_remote_code=True) # trust_remote_code is needed to use the encode method
embeddings_model = embeddings_model.to(embeddings_device)
else:
embeddings_model = SentenceTransformer(model, device=embeddings_device)
print(f"Loaded embedding model: {model}") print(f"Loaded embedding model: {model}")
except Exception as e: except Exception as e:
embeddings_model = None embeddings_model = None

29
extensions/openai/models.py
View File

@ -1,8 +1,9 @@
from modules import shared from modules import shared
from modules.logging_colors import logger from modules.logging_colors import logger
from modules.LoRA import add_lora_to_model
from modules.models import load_model, unload_model from modules.models import load_model, unload_model
from modules.models_settings import get_model_metadata, update_model_parameters from modules.models_settings import get_model_metadata, update_model_parameters
from modules.utils import get_available_models from modules.utils import get_available_loras, get_available_models
def get_current_model_info(): def get_current_model_info():
@ -13,12 +14,17 @@ def get_current_model_info():
def list_models(): def list_models():
return {'model_names': get_available_models()[1:]}
def list_dummy_models():
result = { result = {
"object": "list", "object": "list",
"data": [] "data": []
} }
for model in get_dummy_models() + get_available_models()[1:]: # these are expected by so much, so include some here as a dummy
for model in ['gpt-3.5-turbo', 'text-embedding-ada-002']:
result["data"].append(model_info_dict(model)) result["data"].append(model_info_dict(model))
return result return result
@ -33,13 +39,6 @@ def model_info_dict(model_name: str) -> dict:
} }
def get_dummy_models() -> list:
return [ # these are expected by so much, so include some here as a dummy
'gpt-3.5-turbo',
'text-embedding-ada-002',
]
def _load_model(data): def _load_model(data):
model_name = data["model_name"] model_name = data["model_name"]
args = data["args"] args = data["args"]
@ -67,3 +66,15 @@ def _load_model(data):
logger.info(f"TRUNCATION LENGTH (UPDATED): {shared.settings['truncation_length']}") logger.info(f"TRUNCATION LENGTH (UPDATED): {shared.settings['truncation_length']}")
elif k == 'instruction_template': elif k == 'instruction_template':
logger.info(f"INSTRUCTION TEMPLATE (UPDATED): {shared.settings['instruction_template']}") logger.info(f"INSTRUCTION TEMPLATE (UPDATED): {shared.settings['instruction_template']}")
def list_loras():
return {'lora_names': get_available_loras()[1:]}
def load_loras(lora_names):
add_lora_to_model(lora_names)
def unload_all_loras():
add_lora_to_model([])

100
extensions/openai/script.py
View File

@ -16,6 +16,7 @@ from sse_starlette import EventSourceResponse
import extensions.openai.completions as OAIcompletions import extensions.openai.completions as OAIcompletions
import extensions.openai.embeddings as OAIembeddings import extensions.openai.embeddings as OAIembeddings
import extensions.openai.images as OAIimages import extensions.openai.images as OAIimages
import extensions.openai.logits as OAIlogits
import extensions.openai.models as OAImodels import extensions.openai.models as OAImodels
import extensions.openai.moderations as OAImoderations import extensions.openai.moderations as OAImoderations
from extensions.openai.errors import ServiceUnavailableError from extensions.openai.errors import ServiceUnavailableError
@ -37,8 +38,13 @@ from .typing import (
EmbeddingsResponse, EmbeddingsResponse,
EncodeRequest, EncodeRequest,
EncodeResponse, EncodeResponse,
LoadLorasRequest,
LoadModelRequest, LoadModelRequest,
LogitsRequest,
LogitsResponse,
LoraListResponse,
ModelInfoResponse, ModelInfoResponse,
ModelListResponse,
TokenCountResponse, TokenCountResponse,
to_dict to_dict
) )
@ -60,7 +66,15 @@ def verify_api_key(authorization: str = Header(None)) -> None:
raise HTTPException(status_code=401, detail="Unauthorized") raise HTTPException(status_code=401, detail="Unauthorized")
app = FastAPI(dependencies=[Depends(verify_api_key)]) def verify_admin_key(authorization: str = Header(None)) -> None:
expected_api_key = shared.args.admin_key
if expected_api_key and (authorization is None or authorization != f"Bearer {expected_api_key}"):
raise HTTPException(status_code=401, detail="Unauthorized")
app = FastAPI()
check_key = [Depends(verify_api_key)]
check_admin_key = [Depends(verify_admin_key)]
# Configure CORS settings to allow all origins, methods, and headers # Configure CORS settings to allow all origins, methods, and headers
app.add_middleware( app.add_middleware(
@ -72,12 +86,12 @@ app.add_middleware(
) )
@app.options("/") @app.options("/", dependencies=check_key)
async def options_route(): async def options_route():
return JSONResponse(content="OK") return JSONResponse(content="OK")
@app.post('/v1/completions', response_model=CompletionResponse) @app.post('/v1/completions', response_model=CompletionResponse, dependencies=check_key)
async def openai_completions(request: Request, request_data: CompletionRequest): async def openai_completions(request: Request, request_data: CompletionRequest):
path = request.url.path path = request.url.path
is_legacy = "/generate" in path is_legacy = "/generate" in path
@ -100,7 +114,7 @@ async def openai_completions(request: Request, request_data: CompletionRequest):
return JSONResponse(response) return JSONResponse(response)
@app.post('/v1/chat/completions', response_model=ChatCompletionResponse) @app.post('/v1/chat/completions', response_model=ChatCompletionResponse, dependencies=check_key)
async def openai_chat_completions(request: Request, request_data: ChatCompletionRequest): async def openai_chat_completions(request: Request, request_data: ChatCompletionRequest):
path = request.url.path path = request.url.path
is_legacy = "/generate" in path is_legacy = "/generate" in path
@ -123,14 +137,14 @@ async def openai_chat_completions(request: Request, request_data: ChatCompletion
return JSONResponse(response) return JSONResponse(response)
@app.get("/v1/models") @app.get("/v1/models", dependencies=check_key)
@app.get("/v1/models/{model}") @app.get("/v1/models/{model}", dependencies=check_key)
async def handle_models(request: Request): async def handle_models(request: Request):
path = request.url.path path = request.url.path
is_list = request.url.path.split('?')[0].split('#')[0] == '/v1/models' is_list = request.url.path.split('?')[0].split('#')[0] == '/v1/models'
if is_list: if is_list:
response = OAImodels.list_models() response = OAImodels.list_dummy_models()
else: else:
model_name = path[len('/v1/models/'):] model_name = path[len('/v1/models/'):]
response = OAImodels.model_info_dict(model_name) response = OAImodels.model_info_dict(model_name)
@ -138,7 +152,7 @@ async def handle_models(request: Request):
return JSONResponse(response) return JSONResponse(response)
@app.get('/v1/billing/usage') @app.get('/v1/billing/usage', dependencies=check_key)
def handle_billing_usage(): def handle_billing_usage():
''' '''
Ex. /v1/dashboard/billing/usage?start_date=2023-05-01&end_date=2023-05-31 Ex. /v1/dashboard/billing/usage?start_date=2023-05-01&end_date=2023-05-31
@ -146,7 +160,7 @@ def handle_billing_usage():
return JSONResponse(content={"total_usage": 0}) return JSONResponse(content={"total_usage": 0})
@app.post('/v1/audio/transcriptions') @app.post('/v1/audio/transcriptions', dependencies=check_key)
async def handle_audio_transcription(request: Request): async def handle_audio_transcription(request: Request):
r = sr.Recognizer() r = sr.Recognizer()
@ -176,7 +190,7 @@ async def handle_audio_transcription(request: Request):
return JSONResponse(content=transcription) return JSONResponse(content=transcription)
@app.post('/v1/images/generations') @app.post('/v1/images/generations', dependencies=check_key)
async def handle_image_generation(request: Request): async def handle_image_generation(request: Request):
if not os.environ.get('SD_WEBUI_URL', params.get('sd_webui_url', '')): if not os.environ.get('SD_WEBUI_URL', params.get('sd_webui_url', '')):
@ -192,7 +206,7 @@ async def handle_image_generation(request: Request):
return JSONResponse(response) return JSONResponse(response)
@app.post("/v1/embeddings", response_model=EmbeddingsResponse) @app.post("/v1/embeddings", response_model=EmbeddingsResponse, dependencies=check_key)
async def handle_embeddings(request: Request, request_data: EmbeddingsRequest): async def handle_embeddings(request: Request, request_data: EmbeddingsRequest):
input = request_data.input input = request_data.input
if not input: if not input:
@ -205,7 +219,7 @@ async def handle_embeddings(request: Request, request_data: EmbeddingsRequest):
return JSONResponse(response) return JSONResponse(response)
@app.post("/v1/moderations") @app.post("/v1/moderations", dependencies=check_key)
async def handle_moderations(request: Request): async def handle_moderations(request: Request):
body = await request.json() body = await request.json()
input = body["input"] input = body["input"]
@ -216,37 +230,53 @@ async def handle_moderations(request: Request):
return JSONResponse(response) return JSONResponse(response)
@app.post("/v1/internal/encode", response_model=EncodeResponse) @app.post("/v1/internal/encode", response_model=EncodeResponse, dependencies=check_key)
async def handle_token_encode(request_data: EncodeRequest): async def handle_token_encode(request_data: EncodeRequest):
response = token_encode(request_data.text) response = token_encode(request_data.text)
return JSONResponse(response) return JSONResponse(response)
@app.post("/v1/internal/decode", response_model=DecodeResponse) @app.post("/v1/internal/decode", response_model=DecodeResponse, dependencies=check_key)
async def handle_token_decode(request_data: DecodeRequest): async def handle_token_decode(request_data: DecodeRequest):
response = token_decode(request_data.tokens) response = token_decode(request_data.tokens)
return JSONResponse(response) return JSONResponse(response)
@app.post("/v1/internal/token-count", response_model=TokenCountResponse) @app.post("/v1/internal/token-count", response_model=TokenCountResponse, dependencies=check_key)
async def handle_token_count(request_data: EncodeRequest): async def handle_token_count(request_data: EncodeRequest):
response = token_count(request_data.text) response = token_count(request_data.text)
return JSONResponse(response) return JSONResponse(response)
@app.post("/v1/internal/stop-generation") @app.post("/v1/internal/logits", response_model=LogitsResponse, dependencies=check_key)
async def handle_logits(request_data: LogitsRequest):
'''
Given a prompt, returns the top 50 most likely logits as a dict.
The keys are the tokens, and the values are the probabilities.
'''
response = OAIlogits._get_next_logits(to_dict(request_data))
return JSONResponse(response)
@app.post("/v1/internal/stop-generation", dependencies=check_key)
async def handle_stop_generation(request: Request): async def handle_stop_generation(request: Request):
stop_everything_event() stop_everything_event()
return JSONResponse(content="OK") return JSONResponse(content="OK")
@app.get("/v1/internal/model/info", response_model=ModelInfoResponse) @app.get("/v1/internal/model/info", response_model=ModelInfoResponse, dependencies=check_key)
async def handle_model_info(): async def handle_model_info():
payload = OAImodels.get_current_model_info() payload = OAImodels.get_current_model_info()
return JSONResponse(content=payload) return JSONResponse(content=payload)
@app.post("/v1/internal/model/load") @app.get("/v1/internal/model/list", response_model=ModelListResponse, dependencies=check_admin_key)
async def handle_list_models():
payload = OAImodels.list_models()
return JSONResponse(content=payload)
@app.post("/v1/internal/model/load", dependencies=check_admin_key)
async def handle_load_model(request_data: LoadModelRequest): async def handle_load_model(request_data: LoadModelRequest):
''' '''
This endpoint is experimental and may change in the future. This endpoint is experimental and may change in the future.
@ -283,9 +313,30 @@ async def handle_load_model(request_data: LoadModelRequest):
return HTTPException(status_code=400, detail="Failed to load the model.") return HTTPException(status_code=400, detail="Failed to load the model.")
@app.post("/v1/internal/model/unload") @app.post("/v1/internal/model/unload", dependencies=check_admin_key)
async def handle_unload_model(): async def handle_unload_model():
unload_model() unload_model()
@app.get("/v1/internal/lora/list", response_model=LoraListResponse, dependencies=check_admin_key)
async def handle_list_loras():
response = OAImodels.list_loras()
return JSONResponse(content=response)
@app.post("/v1/internal/lora/load", dependencies=check_admin_key)
async def handle_load_loras(request_data: LoadLorasRequest):
try:
OAImodels.load_loras(request_data.lora_names)
return JSONResponse(content="OK")
except:
traceback.print_exc()
return HTTPException(status_code=400, detail="Failed to apply the LoRA(s).")
@app.post("/v1/internal/lora/unload", dependencies=check_admin_key)
async def handle_unload_loras():
OAImodels.unload_all_loras()
return JSONResponse(content="OK") return JSONResponse(content="OK")
@ -308,10 +359,19 @@ def run_server():
logger.info(f'OpenAI-compatible API URL:\n\nhttp://{server_addr}:{port}\n') logger.info(f'OpenAI-compatible API URL:\n\nhttp://{server_addr}:{port}\n')
if shared.args.api_key: if shared.args.api_key:
if not shared.args.admin_key:
shared.args.admin_key = shared.args.api_key
logger.info(f'OpenAI API key:\n\n{shared.args.api_key}\n') logger.info(f'OpenAI API key:\n\n{shared.args.api_key}\n')
if shared.args.admin_key:
logger.info(f'OpenAI API admin key (for loading/unloading models):\n\n{shared.args.admin_key}\n')
uvicorn.run(app, host=server_addr, port=port, ssl_certfile=ssl_certfile, ssl_keyfile=ssl_keyfile) uvicorn.run(app, host=server_addr, port=port, ssl_certfile=ssl_certfile, ssl_keyfile=ssl_keyfile)
def setup(): def setup():
Thread(target=run_server, daemon=True).start() if shared.args.nowebui:
run_server()
else:
Thread(target=run_server, daemon=True).start()

94
extensions/openai/typing.py
View File

@ -122,38 +122,6 @@ class ChatCompletionResponse(BaseModel):
usage: dict usage: dict
class EncodeRequest(BaseModel):
text: str
class DecodeRequest(BaseModel):
tokens: List[int]
class EncodeResponse(BaseModel):
tokens: List[int]
length: int
class DecodeResponse(BaseModel):
text: str
class TokenCountResponse(BaseModel):
length: int
class ModelInfoResponse(BaseModel):
model_name: str
lora_names: List[str]
class LoadModelRequest(BaseModel):
model_name: str
args: dict | None = None
settings: dict | None = None
class EmbeddingsRequest(BaseModel): class EmbeddingsRequest(BaseModel):
input: str | List[str] input: str | List[str]
model: str | None = Field(default=None, description="Unused parameter. To change the model, set the OPENEDAI_EMBEDDING_MODEL and OPENEDAI_EMBEDDING_DEVICE environment variables before starting the server.") model: str | None = Field(default=None, description="Unused parameter. To change the model, set the OPENEDAI_EMBEDDING_MODEL and OPENEDAI_EMBEDDING_DEVICE environment variables before starting the server.")
@ -167,6 +135,68 @@ class EmbeddingsResponse(BaseModel):
object: str = "embedding" object: str = "embedding"
class EncodeRequest(BaseModel):
text: str
class EncodeResponse(BaseModel):
tokens: List[int]
length: int
class DecodeRequest(BaseModel):
tokens: List[int]
class DecodeResponse(BaseModel):
text: str
class TokenCountResponse(BaseModel):
length: int
class LogitsRequestParams(BaseModel):
prompt: str
use_samplers: bool = False
frequency_penalty: float | None = 0
max_tokens: int | None = 16
presence_penalty: float | None = 0
temperature: float | None = 1
top_p: float | None = 1
class LogitsRequest(GenerationOptions, LogitsRequestParams):
pass
class LogitsResponse(BaseModel):
logits: dict
class ModelInfoResponse(BaseModel):
model_name: str
lora_names: List[str]
class ModelListResponse(BaseModel):
model_names: List[str]
class LoadModelRequest(BaseModel):
model_name: str
args: dict | None = None
settings: dict | None = None
class LoraListResponse(BaseModel):
lora_names: List[str]
class LoadLorasRequest(BaseModel):
lora_names: List[str]
def to_json(obj): def to_json(obj):
return json.dumps(obj.__dict__, indent=4) return json.dumps(obj.__dict__, indent=4)

38
js/main.js
View File

@ -312,6 +312,10 @@ document.addEventListener("click", function (event) {
if (!isMouseOverButtonOrMenu() && menu.style.display === "flex") { if (!isMouseOverButtonOrMenu() && menu.style.display === "flex") {
hideMenu(); hideMenu();
} }
if (event.target.classList.contains("pfp_character")) {
toggleBigPicture();
}
}); });
//------------------------------------------------ //------------------------------------------------
@ -335,3 +339,37 @@ document.getElementById("show-controls").parentNode.style.bottom = "0px";
// Focus on the chat input // Focus on the chat input
//------------------------------------------------ //------------------------------------------------
document.querySelector("#chat-input textarea").focus(); document.querySelector("#chat-input textarea").focus();
//------------------------------------------------
// Show enlarged character picture when the profile
// picture is clicked on
//------------------------------------------------
let bigPictureVisible = false;
function addBigPicture() {
var imgElement = document.createElement("img");
var timestamp = new Date().getTime();
imgElement.src = "/file/cache/pfp_character.png?time=" + timestamp;
imgElement.classList.add("bigProfilePicture");
var imgElementParent = document.getElementById("chat").parentNode.parentNode.parentNode.parentNode.parentNode.parentNode.parentNode;
imgElementParent.appendChild(imgElement);
}
function deleteBigPicture() {
var bigProfilePictures = document.querySelectorAll('.bigProfilePicture');
bigProfilePictures.forEach(function (element) {
element.parentNode.removeChild(element);
});
}
function toggleBigPicture() {
if(bigPictureVisible) {
deleteBigPicture();
bigPictureVisible = false;
} else {
addBigPicture();
bigPictureVisible = true;
}
}

6
js/show_controls.js
View File

@ -10,6 +10,12 @@ function toggle_controls(value) {
chatParent.classList.remove("bigchat"); chatParent.classList.remove("bigchat");
document.getElementById("chat-input-row").classList.remove("bigchat"); document.getElementById("chat-input-row").classList.remove("bigchat");
document.getElementById("chat-col").classList.remove("bigchat"); document.getElementById("chat-col").classList.remove("bigchat");
let gallery_element = document.getElementById('gallery-extension');
if (gallery_element) {
gallery_element.style.display = 'block';
}
} else { } else {
belowChatInput.forEach(element => { belowChatInput.forEach(element => {
element.style.display = "none"; element.style.display = "none";

7
js/update_big_picture.js Normal file
View File

@ -0,0 +1,7 @@
function updateBigPicture() {
var existingElement = document.querySelector('.bigProfilePicture');
if (existingElement) {
var timestamp = new Date().getTime();
existingElement.src = "/file/cache/pfp_character.png?time=" + timestamp;
}
}

10
modules/LoRA.py
View File

@ -145,14 +145,12 @@ def add_lora_transformers(lora_names):
if len(lora_names) > 1: if len(lora_names) > 1:
merge_loras() merge_loras()
shared.lora_names = lora_names
return return
# If any LoRA needs to be removed, start over # If any LoRA needs to be removed, start over
if len(removed_set) > 0: if len(removed_set) > 0:
# shared.model may no longer be PeftModel shared.model = shared.model.unload()
if hasattr(shared.model, 'disable_adapter'):
shared.model.disable_adapter()
shared.model = shared.model.base_model.model
if len(lora_names) > 0: if len(lora_names) > 0:
params = {} params = {}
@ -172,8 +170,6 @@ def add_lora_transformers(lora_names):
if len(lora_names) > 1: if len(lora_names) > 1:
merge_loras() merge_loras()
shared.lora_names = lora_names
if not shared.args.load_in_8bit and not shared.args.cpu: if not shared.args.load_in_8bit and not shared.args.cpu:
shared.model.half() shared.model.half()
if not hasattr(shared.model, "hf_device_map"): if not hasattr(shared.model, "hf_device_map"):
@ -186,6 +182,8 @@ def add_lora_transformers(lora_names):
else: else:
shared.model = shared.model.cuda() shared.model = shared.model.cuda()
shared.lora_names = lora_names
def merge_loras(): def merge_loras():
if len(list({shared.model.peft_config[adapter].r for adapter in shared.model.peft_config.keys()})) > 1: if len(list({shared.model.peft_config[adapter].r for adapter in shared.model.peft_config.keys()})) > 1:

23
modules/chat.py
View File

@ -91,7 +91,13 @@ def generate_chat_prompt(user_input, state, **kwargs):
if state['mode'] == 'chat-instruct': if state['mode'] == 'chat-instruct':
wrapper = '' wrapper = ''
command = state['chat-instruct_command'].replace('<|character|>', state['name2'] if not impersonate else state['name1']) command = state['chat-instruct_command'].replace('<|character|>', state['name2'] if not impersonate else state['name1'])
wrapper += state['context_instruct'] context_instruct = state['context_instruct']
if state['custom_system_message'].strip() != '':
context_instruct = context_instruct.replace('<|system-message|>', state['custom_system_message'])
else:
context_instruct = context_instruct.replace('<|system-message|>', state['system_message'])
wrapper += context_instruct
wrapper += all_substrings['instruct']['user_turn'].replace('<|user-message|>', command) wrapper += all_substrings['instruct']['user_turn'].replace('<|user-message|>', command)
wrapper += all_substrings['instruct']['bot_turn_stripped'] wrapper += all_substrings['instruct']['bot_turn_stripped']
if impersonate: if impersonate:
@ -539,9 +545,13 @@ def generate_pfp_cache(character):
for path in [Path(f"characters/{character}.{extension}") for extension in ['png', 'jpg', 'jpeg']]: for path in [Path(f"characters/{character}.{extension}") for extension in ['png', 'jpg', 'jpeg']]:
if path.exists(): if path.exists():
img = make_thumbnail(Image.open(path)) original_img = Image.open(path)
img.save(Path('cache/pfp_character.png'), format='PNG') original_img.save(Path('cache/pfp_character.png'), format='PNG')
return img
thumb = make_thumbnail(original_img)
thumb.save(Path('cache/pfp_character_thumb.png'), format='PNG')
return thumb
return None return None
@ -570,8 +580,9 @@ def load_character(character, name1, name2, instruct=False):
file_contents = open(filepath, 'r', encoding='utf-8').read() file_contents = open(filepath, 'r', encoding='utf-8').read()
data = json.loads(file_contents) if extension == "json" else yaml.safe_load(file_contents) data = json.loads(file_contents) if extension == "json" else yaml.safe_load(file_contents)
if Path("cache/pfp_character.png").exists() and not instruct: for path in [Path("cache/pfp_character.png"), Path("cache/pfp_character_thumb.png")]:
Path("cache/pfp_character.png").unlink() if path.exists() and not instruct:
path.unlink()
picture = generate_pfp_cache(character) picture = generate_pfp_cache(character)

2
modules/html_generator.py
View File

@ -225,7 +225,7 @@ def generate_cai_chat_html(history, name1, name2, style, reset_cache=False):
output = f'<style>{chat_styles[style]}</style><div class="chat" id="chat"><div class="messages">' output = f'<style>{chat_styles[style]}</style><div class="chat" id="chat"><div class="messages">'
# We use ?name2 and ?time.time() to force the browser to reset caches # We use ?name2 and ?time.time() to force the browser to reset caches
img_bot = f'<img src="file/cache/pfp_character.png?{name2}">' if Path("cache/pfp_character.png").exists() else '' img_bot = f'<img src="file/cache/pfp_character_thumb.png?{name2}" class="pfp_character">' if Path("cache/pfp_character_thumb.png").exists() else ''
img_me = f'<img src="file/cache/pfp_me.png?{time.time() if reset_cache else ""}">' if Path("cache/pfp_me.png").exists() else '' img_me = f'<img src="file/cache/pfp_me.png?{time.time() if reset_cache else ""}">' if Path("cache/pfp_me.png").exists() else ''
for i, _row in enumerate(history): for i, _row in enumerate(history):

11
modules/llamacpp_hf.py
View File

@ -39,7 +39,7 @@ class LlamacppHF(PreTrainedModel):
'n_tokens': self.model.n_tokens, 'n_tokens': self.model.n_tokens,
'input_ids': self.model.input_ids, 'input_ids': self.model.input_ids,
'scores': self.model.scores, 'scores': self.model.scores,
'ctx': self.model.ctx 'ctx': self.model._ctx
} }
if shared.args.cfg_cache: if shared.args.cfg_cache:
@ -65,7 +65,7 @@ class LlamacppHF(PreTrainedModel):
'n_tokens': self.model.n_tokens, 'n_tokens': self.model.n_tokens,
'input_ids': self.model.input_ids, 'input_ids': self.model.input_ids,
'scores': self.model.scores, 'scores': self.model.scores,
'ctx': self.model.ctx 'ctx': self.model._ctx
}) })
def save_negative_cache(self): def save_negative_cache(self):
@ -73,20 +73,20 @@ class LlamacppHF(PreTrainedModel):
'n_tokens': self.model.n_tokens, 'n_tokens': self.model.n_tokens,
'input_ids': self.model.input_ids, 'input_ids': self.model.input_ids,
'scores': self.model.scores, 'scores': self.model.scores,
'ctx': self.model.ctx 'ctx': self.model._ctx
}) })
def load_cache(self): def load_cache(self):
self.model.n_tokens = self.llamacpp_cache['n_tokens'] self.model.n_tokens = self.llamacpp_cache['n_tokens']
self.model.input_ids = self.llamacpp_cache['input_ids'] self.model.input_ids = self.llamacpp_cache['input_ids']
self.model.scores = self.llamacpp_cache['scores'] self.model.scores = self.llamacpp_cache['scores']
self.model.ctx = self.llamacpp_cache['ctx'] self.model._ctx = self.llamacpp_cache['ctx']
def load_negative_cache(self): def load_negative_cache(self):
self.model.n_tokens = self.llamacpp_cache_negative['n_tokens'] self.model.n_tokens = self.llamacpp_cache_negative['n_tokens']
self.model.input_ids = self.llamacpp_cache_negative['input_ids'] self.model.input_ids = self.llamacpp_cache_negative['input_ids']
self.model.scores = self.llamacpp_cache_negative['scores'] self.model.scores = self.llamacpp_cache_negative['scores']
self.model.ctx = self.llamacpp_cache_negative['ctx'] self.model._ctx = self.llamacpp_cache_negative['ctx']
@property @property
def device(self) -> torch.device: def device(self) -> torch.device:
@ -192,7 +192,6 @@ class LlamacppHF(PreTrainedModel):
params = { params = {
'model_path': str(model_file), 'model_path': str(model_file),
'n_ctx': shared.args.n_ctx, 'n_ctx': shared.args.n_ctx,
'seed': int(shared.args.llama_cpp_seed),
'n_threads': shared.args.threads or None, 'n_threads': shared.args.threads or None,
'n_threads_batch': shared.args.threads_batch or None, 'n_threads_batch': shared.args.threads_batch or None,
'n_batch': shared.args.n_batch, 'n_batch': shared.args.n_batch,

10
modules/llamacpp_model.py
View File

@ -74,7 +74,6 @@ class LlamaCppModel:
params = { params = {
'model_path': str(path), 'model_path': str(path),
'n_ctx': shared.args.n_ctx, 'n_ctx': shared.args.n_ctx,
'seed': int(shared.args.llama_cpp_seed),
'n_threads': shared.args.threads or None, 'n_threads': shared.args.threads or None,
'n_threads_batch': shared.args.threads_batch or None, 'n_threads_batch': shared.args.threads_batch or None,
'n_batch': shared.args.n_batch, 'n_batch': shared.args.n_batch,
@ -144,15 +143,16 @@ class LlamaCppModel:
max_tokens=state['max_new_tokens'], max_tokens=state['max_new_tokens'],
temperature=state['temperature'], temperature=state['temperature'],
top_p=state['top_p'], top_p=state['top_p'],
top_k=state['top_k'],
repeat_penalty=state['repetition_penalty'],
presence_penalty=state['presence_penalty'],
frequency_penalty=state['frequency_penalty'], frequency_penalty=state['frequency_penalty'],
presence_penalty=state['presence_penalty'],
repeat_penalty=state['repetition_penalty'],
top_k=state['top_k'],
stream=True,
seed=int(state['seed']) if state['seed'] != -1 else None,
tfs_z=state['tfs'], tfs_z=state['tfs'],
mirostat_mode=int(state['mirostat_mode']), mirostat_mode=int(state['mirostat_mode']),
mirostat_tau=state['mirostat_tau'], mirostat_tau=state['mirostat_tau'],
mirostat_eta=state['mirostat_eta'], mirostat_eta=state['mirostat_eta'],
stream=True,
logits_processor=logit_processors, logits_processor=logit_processors,
grammar=self.grammar grammar=self.grammar
) )

2
modules/loaders.py
View File

@ -99,7 +99,6 @@ loaders_and_params = OrderedDict({
'no_mmap', 'no_mmap',
'mlock', 'mlock',
'no_mul_mat_q', 'no_mul_mat_q',
'llama_cpp_seed',
'alpha_value', 'alpha_value',
'rope_freq_base', 'rope_freq_base',
'compress_pos_emb', 'compress_pos_emb',
@ -366,6 +365,7 @@ loaders_samplers = {
'repetition_penalty', 'repetition_penalty',
'presence_penalty', 'presence_penalty',
'frequency_penalty', 'frequency_penalty',
'seed',
'mirostat_mode', 'mirostat_mode',
'mirostat_tau', 'mirostat_tau',
'mirostat_eta', 'mirostat_eta',

18
modules/logits.py
View File

@ -8,7 +8,7 @@ from modules.text_generation import generate_reply
global_scores = None global_scores = None
def get_next_logits(prompt, state, use_samplers, previous): def get_next_logits(prompt, state, use_samplers, previous, return_dict=False):
if shared.model is None: if shared.model is None:
logger.error("No model is loaded! Select one in the Model tab.") logger.error("No model is loaded! Select one in the Model tab.")
return 'Error: No model is loaded1 Select one in the Model tab.', previous return 'Error: No model is loaded1 Select one in the Model tab.', previous
@ -56,8 +56,16 @@ def get_next_logits(prompt, state, use_samplers, previous):
topk_indices = [i.expand((1, 1)) for i in topk_indices] topk_indices = [i.expand((1, 1)) for i in topk_indices]
tokens = [shared.tokenizer.decode(i) for i in topk_indices] tokens = [shared.tokenizer.decode(i) for i in topk_indices]
output = ''
for row in list(zip(topk_values, tokens)):
output += f"{row[0]} - {repr(row[1])}\n"
return output, previous if return_dict:
output = {}
for row in list(zip(topk_values, tokens)):
output[row[1]] = row[0]
return output
else:
output = ''
for row in list(zip(topk_values, tokens)):
output += f"{row[0]} - {repr(row[1])}\n"
return output, previous

43
modules/presets.py
View File

@ -1,8 +1,12 @@
import functools import functools
import random
from pathlib import Path from pathlib import Path
import yaml import yaml
from modules import shared
from modules.loaders import loaders_samplers
def default_preset(): def default_preset():
return { return {
@ -63,6 +67,45 @@ def load_preset_for_ui(name, state):
return state, *[generate_params[k] for k in presets_params()] return state, *[generate_params[k] for k in presets_params()]
def random_preset(state):
params_and_values = {
'remove_tail_tokens': {
'top_p': [0.5, 0.8, 0.9, 0.95, 0.99],
'min_p': [0.5, 0.2, 0.1, 0.05, 0.01],
'top_k': [3, 5, 10, 20, 30, 40],
'typical_p': [0.2, 0.575, 0.95],
'tfs': [0.5, 0.8, 0.9, 0.95, 0.99],
'top_a': [0.5, 0.2, 0.1, 0.05, 0.01],
'epsilon_cutoff': [1, 3, 5, 7, 9],
'eta_cutoff': [3, 6, 9, 12, 15, 18],
},
'flatten_distribution': {
'temperature': [0.5, 0.7, 0.8, 1, 1.2, 1.5, 2.0],
},
'repetition': {
'repetition_penalty': [1, 1.05, 1.1, 1.15, 1.20, 1.25],
'presence_penalty': [0, 0.1, 0.2, 0.4, 0.6, 0.8, 1.0, 2.0],
'frequency_penalty': [0, 0.1, 0.2, 0.4, 0.6, 0.8, 1.0, 2.0],
},
'other': {
'temperature_last': [True, False],
}
}
generate_params = default_preset()
for cat in params_and_values:
choices = list(params_and_values[cat].keys())
if shared.args.loader is not None:
choices = [x for x in choices if x in loaders_samplers[shared.args.loader]]
if len(choices) > 0:
choice = random.choice(choices)
generate_params[choice] = random.choice(params_and_values[cat][choice])
state.update(generate_params)
return state, *[generate_params[k] for k in presets_params()]
def generate_preset_yaml(state): def generate_preset_yaml(state):
defaults = default_preset() defaults = default_preset()
data = {k: state[k] for k in presets_params()} data = {k: state[k] for k in presets_params()}

6
modules/shared.py
View File

@ -112,7 +112,6 @@ parser.add_argument('--no-mmap', action='store_true', help='Prevent mmap from be
parser.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.') parser.add_argument('--mlock', action='store_true', help='Force the system to keep the model in RAM.')
parser.add_argument('--n-gpu-layers', type=int, default=0, help='Number of layers to offload to the GPU.') parser.add_argument('--n-gpu-layers', type=int, default=0, help='Number of layers to offload to the GPU.')
parser.add_argument('--tensor_split', type=str, default=None, help='Split the model across multiple GPUs. Comma-separated list of proportions. Example: 18,17.') parser.add_argument('--tensor_split', type=str, default=None, help='Split the model across multiple GPUs. Comma-separated list of proportions. Example: 18,17.')
parser.add_argument('--llama_cpp_seed', type=int, default=0, help='Seed for llama-cpp models. Default is 0 (random).')
parser.add_argument('--numa', action='store_true', help='Activate NUMA task allocation for llama.cpp.') parser.add_argument('--numa', action='store_true', help='Activate NUMA task allocation for llama.cpp.')
parser.add_argument('--logits_all', action='store_true', help='Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower.') parser.add_argument('--logits_all', action='store_true', help='Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower.')
parser.add_argument('--cache-capacity', type=str, help='Maximum cache capacity (llama-cpp-python). Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.') parser.add_argument('--cache-capacity', type=str, help='Maximum cache capacity (llama-cpp-python). Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.')
@ -171,6 +170,8 @@ parser.add_argument('--public-api', action='store_true', help='Create a public U
parser.add_argument('--public-api-id', type=str, help='Tunnel ID for named Cloudflare Tunnel. Use together with public-api option.', default=None) parser.add_argument('--public-api-id', type=str, help='Tunnel ID for named Cloudflare Tunnel. Use together with public-api option.', default=None)
parser.add_argument('--api-port', type=int, default=5000, help='The listening port for the API.') parser.add_argument('--api-port', type=int, default=5000, help='The listening port for the API.')
parser.add_argument('--api-key', type=str, default='', help='API authentication key.') parser.add_argument('--api-key', type=str, default='', help='API authentication key.')
parser.add_argument('--admin-key', type=str, default='', help='API authentication key for admin tasks like loading and unloading models. If not set, will be the same as --api-key.')
parser.add_argument('--nowebui', action='store_true', help='Do not launch the Gradio UI. Useful for launching the API in standalone mode.')
# Multimodal # Multimodal
parser.add_argument('--multimodal-pipeline', type=str, default=None, help='The multimodal pipeline to use. Examples: llava-7b, llava-13b.') parser.add_argument('--multimodal-pipeline', type=str, default=None, help='The multimodal pipeline to use. Examples: llava-7b, llava-13b.')
@ -182,6 +183,7 @@ parser.add_argument('--no-stream', action='store_true', help='DEPRECATED')
parser.add_argument('--mul_mat_q', action='store_true', help='DEPRECATED') parser.add_argument('--mul_mat_q', action='store_true', help='DEPRECATED')
parser.add_argument('--api-blocking-port', type=int, default=5000, help='DEPRECATED') parser.add_argument('--api-blocking-port', type=int, default=5000, help='DEPRECATED')
parser.add_argument('--api-streaming-port', type=int, default=5005, help='DEPRECATED') parser.add_argument('--api-streaming-port', type=int, default=5005, help='DEPRECATED')
parser.add_argument('--llama_cpp_seed', type=int, default=0, help='DEPRECATED')
parser.add_argument('--use_fast', action='store_true', help='DEPRECATED') parser.add_argument('--use_fast', action='store_true', help='DEPRECATED')
args = parser.parse_args() args = parser.parse_args()
@ -200,7 +202,7 @@ for k in ['notebook', 'chat', 'no_stream', 'mul_mat_q', 'use_fast']:
# Security warnings # Security warnings
if args.trust_remote_code: if args.trust_remote_code:
logger.warning('trust_remote_code is enabled. This is dangerous.') logger.warning('trust_remote_code is enabled. This is dangerous.')
if 'COLAB_GPU' not in os.environ: if 'COLAB_GPU' not in os.environ and not args.nowebui:
if args.share: if args.share:
logger.warning("The gradio \"share link\" feature uses a proprietary executable to create a reverse tunnel. Use it with care.") logger.warning("The gradio \"share link\" feature uses a proprietary executable to create a reverse tunnel. Use it with care.")
if any((args.listen, args.share)) and not any((args.gradio_auth, args.gradio_auth_path)): if any((args.listen, args.share)) and not any((args.gradio_auth, args.gradio_auth_path)):

3
modules/ui.py
View File

@ -20,6 +20,8 @@ with open(Path(__file__).resolve().parent / '../js/switch_tabs.js', 'r') as f:
switch_tabs_js = f.read() switch_tabs_js = f.read()
with open(Path(__file__).resolve().parent / '../js/show_controls.js', 'r') as f: with open(Path(__file__).resolve().parent / '../js/show_controls.js', 'r') as f:
show_controls_js = f.read() show_controls_js = f.read()
with open(Path(__file__).resolve().parent / '../js/update_big_picture.js', 'r') as f:
update_big_picture_js = f.read()
refresh_symbol = '🔄' refresh_symbol = '🔄'
delete_symbol = '🗑️' delete_symbol = '🗑️'
@ -80,7 +82,6 @@ def list_model_elements():
'n_gpu_layers', 'n_gpu_layers',
'tensor_split', 'tensor_split',
'n_ctx', 'n_ctx',
'llama_cpp_seed',
'gpu_split', 'gpu_split',
'max_seq_len', 'max_seq_len',
'compress_pos_emb', 'compress_pos_emb',

3
modules/ui_chat.py
View File

@ -275,7 +275,8 @@ def create_event_handlers():
ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then( ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
chat.load_latest_history, gradio('interface_state'), gradio('history')).then( chat.load_latest_history, gradio('interface_state'), gradio('history')).then(
chat.redraw_html, gradio(reload_arr), gradio('display')).then( chat.redraw_html, gradio(reload_arr), gradio('display')).then(
lambda x: gr.update(choices=(histories := chat.find_all_histories(x)), value=histories[0]), gradio('interface_state'), gradio('unique_id')) lambda x: gr.update(choices=(histories := chat.find_all_histories(x)), value=histories[0]), gradio('interface_state'), gradio('unique_id')).then(
lambda: None, None, None, _js=f'() => {{{ui.update_big_picture_js}; updateBigPicture()}}')
shared.gradio['mode'].change( shared.gradio['mode'].change(
lambda x: gr.update(visible=x != 'instruct'), gradio('mode'), gradio('chat_style'), show_progress=False).then( lambda x: gr.update(visible=x != 'instruct'), gradio('mode'), gradio('chat_style'), show_progress=False).then(

22
modules/ui_file_saving.py
View File

@ -37,6 +37,14 @@ def create_ui():
shared.gradio['delete_character_confirm'] = gr.Button('Delete', elem_classes="small-button", variant='stop', interactive=not mu) shared.gradio['delete_character_confirm'] = gr.Button('Delete', elem_classes="small-button", variant='stop', interactive=not mu)
shared.gradio['delete_character_cancel'] = gr.Button('Cancel', elem_classes="small-button") shared.gradio['delete_character_cancel'] = gr.Button('Cancel', elem_classes="small-button")
# Preset saver
with gr.Group(visible=False, elem_classes='file-saver') as shared.gradio['preset_saver']:
shared.gradio['save_preset_filename'] = gr.Textbox(lines=1, label='File name', info='The preset will be saved to your presets/ folder with this base filename.')
shared.gradio['save_preset_contents'] = gr.Textbox(lines=10, label='File contents')
with gr.Row():
shared.gradio['save_preset_confirm'] = gr.Button('Save', elem_classes="small-button", variant='primary', interactive=not mu)
shared.gradio['save_preset_cancel'] = gr.Button('Cancel', elem_classes="small-button")
def create_event_handlers(): def create_event_handlers():
shared.gradio['save_confirm'].click( shared.gradio['save_confirm'].click(
@ -65,10 +73,16 @@ def create_event_handlers():
shared.gradio['save_preset'].click( shared.gradio['save_preset'].click(
ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then( ui.gather_interface_values, gradio(shared.input_elements), gradio('interface_state')).then(
presets.generate_preset_yaml, gradio('interface_state'), gradio('save_contents')).then( presets.generate_preset_yaml, gradio('interface_state'), gradio('save_preset_contents')).then(
lambda: 'presets/', None, gradio('save_root')).then( lambda: 'My Preset', None, gradio('save_preset_filename')).then(
lambda: 'My Preset.yaml', None, gradio('save_filename')).then( lambda: gr.update(visible=True), None, gradio('preset_saver'))
lambda: gr.update(visible=True), None, gradio('file_saver'))
shared.gradio['save_preset_confirm'].click(
lambda x, y: utils.save_file(f'presets/{x}.yaml', y), gradio('save_preset_filename', 'save_preset_contents'), None).then(
lambda: gr.update(visible=False), None, gradio('preset_saver')).then(
lambda x: gr.update(choices=utils.get_available_presets(), value=x), gradio('save_preset_filename'), gradio('preset_menu'))
shared.gradio['save_preset_cancel'].click(lambda: gr.update(visible=False), None, gradio('preset_saver'))
shared.gradio['delete_preset'].click( shared.gradio['delete_preset'].click(
lambda x: f'{x}.yaml', gradio('preset_menu'), gradio('delete_filename')).then( lambda x: f'{x}.yaml', gradio('preset_menu'), gradio('delete_filename')).then(

1
modules/ui_model_menu.py
View File

@ -120,7 +120,6 @@ def create_ui():
shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit", value=shared.args.load_in_4bit) shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit", value=shared.args.load_in_4bit)
shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant) shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant)
shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17') shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17')
shared.gradio['llama_cpp_seed'] = gr.Number(label='Seed (0 for random)', value=shared.args.llama_cpp_seed)
shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='To enable this option, start the web UI with the --trust-remote-code flag. It is necessary for some models.', interactive=shared.args.trust_remote_code) shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='To enable this option, start the web UI with the --trust-remote-code flag. It is necessary for some models.', interactive=shared.args.trust_remote_code)
shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Create an additional cache for CFG negative prompts.') shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Create an additional cache for CFG negative prompts.')
shared.gradio['logits_all'] = gr.Checkbox(label="logits_all", value=shared.args.logits_all, info='Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower.') shared.gradio['logits_all'] = gr.Checkbox(label="logits_all", value=shared.args.logits_all, info='Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower.')

2
modules/ui_parameters.py
View File

@ -18,6 +18,7 @@ def create_ui(default_preset):
ui.create_refresh_button(shared.gradio['preset_menu'], lambda: None, lambda: {'choices': utils.get_available_presets()}, 'refresh-button', interactive=not mu) ui.create_refresh_button(shared.gradio['preset_menu'], lambda: None, lambda: {'choices': utils.get_available_presets()}, 'refresh-button', interactive=not mu)
shared.gradio['save_preset'] = gr.Button('💾', elem_classes='refresh-button', interactive=not mu) shared.gradio['save_preset'] = gr.Button('💾', elem_classes='refresh-button', interactive=not mu)
shared.gradio['delete_preset'] = gr.Button('🗑️', elem_classes='refresh-button', interactive=not mu) shared.gradio['delete_preset'] = gr.Button('🗑️', elem_classes='refresh-button', interactive=not mu)
shared.gradio['random_preset'] = gr.Button('🎲', elem_classes='refresh-button')
with gr.Column(): with gr.Column():
shared.gradio['filter_by_loader'] = gr.Dropdown(label="Filter by loader", choices=["All"] + list(loaders.loaders_and_params.keys()), value="All", elem_classes='slim-dropdown') shared.gradio['filter_by_loader'] = gr.Dropdown(label="Filter by loader", choices=["All"] + list(loaders.loaders_and_params.keys()), value="All", elem_classes='slim-dropdown')
@ -90,6 +91,7 @@ def create_ui(default_preset):
def create_event_handlers(): def create_event_handlers():
shared.gradio['filter_by_loader'].change(loaders.blacklist_samplers, gradio('filter_by_loader'), gradio(loaders.list_all_samplers()), show_progress=False) shared.gradio['filter_by_loader'].change(loaders.blacklist_samplers, gradio('filter_by_loader'), gradio(loaders.list_all_samplers()), show_progress=False)
shared.gradio['preset_menu'].change(presets.load_preset_for_ui, gradio('preset_menu', 'interface_state'), gradio('interface_state') + gradio(presets.presets_params())) shared.gradio['preset_menu'].change(presets.load_preset_for_ui, gradio('preset_menu', 'interface_state'), gradio('interface_state') + gradio(presets.presets_params()))
shared.gradio['random_preset'].click(presets.random_preset, gradio('interface_state'), gradio('interface_state') + gradio(presets.presets_params()))
shared.gradio['grammar_file'].change(load_grammar, gradio('grammar_file'), gradio('grammar_string')) shared.gradio['grammar_file'].change(load_grammar, gradio('grammar_file'), gradio('grammar_string'))

32
requirements.txt
View File

@ -27,14 +27,14 @@ bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, AVX2) # llama-cpp-python (CPU only, AVX2)
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
# CUDA wheels # CUDA wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
@ -67,14 +67,14 @@ https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"

24
requirements_amd.txt
View File

@ -27,14 +27,14 @@ bitsandbytes==0.38.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, AVX2) # llama-cpp-python (CPU only, AVX2)
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
# AMD wheels # AMD wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
@ -45,10 +45,10 @@ https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/jllllll/exllama/releases/download/0.0.18/exllama-0.0.18+rocm5.6-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.11+rocm5.6.1-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.18+rocm5.6.1-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.11+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.18+rocm5.6.1-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.11+rocm5.6.1-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.18+rocm5.6.1-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.11+rocm5.6.1-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.18+rocm5.6.1-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"

16
requirements_amd_noavx2.txt
View File

@ -27,14 +27,14 @@ bitsandbytes==0.38.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.38.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, no AVX2) # llama-cpp-python (CPU only, no AVX2)
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
# AMD wheels # AMD wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"

28
requirements_apple_intel.txt
View File

@ -27,19 +27,15 @@ bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
# Mac wheels # Mac wheels
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp39-cp39-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp39-cp39-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp38-cp38-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp38-cp38-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp311-cp311-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp311-cp311-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp39-cp39-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp39-cp39-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp38-cp38-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp38-cp38-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp311-cp311-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp39-cp39-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp39-cp39-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp38-cp38-macosx_13_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp38-cp38-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp39-cp39-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp38-cp38-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.8"

32
requirements_apple_silicon.txt
View File

@ -27,19 +27,19 @@ bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
# Mac wheels # Mac wheels
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp39-cp39-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp39-cp39-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp38-cp38-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp38-cp38-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp311-cp311-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp311-cp311-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp39-cp39-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp39-cp39-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp38-cp38-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp38-cp38-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp311-cp311-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp311-cp311-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp39-cp39-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp39-cp39-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp38-cp38-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp38-cp38-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp39-cp39-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp39-cp39-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.11-cp38-cp38-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.18-cp38-cp38-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.8"

16
requirements_cpu_only.txt
View File

@ -27,11 +27,11 @@ bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, AVX2) # llama-cpp-python (CPU only, AVX2)
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-manylinux_2_17_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.11/llama_cpp_python-0.2.11-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" https://github.com/abetlen/llama-cpp-python/releases/download/v0.2.18/llama_cpp_python-0.2.18-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"

16
requirements_cpu_only_noavx2.txt
View File

@ -27,11 +27,11 @@ bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, no AVX2) # llama-cpp-python (CPU only, no AVX2)
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"

32
requirements_noavx2.txt
View File

@ -27,14 +27,14 @@ bitsandbytes==0.41.1; platform_system != "Windows"
https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows" https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl; platform_system == "Windows"
# llama-cpp-python (CPU only, no AVX2) # llama-cpp-python (CPU only, no AVX2)
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.11+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.18+cpuavx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
# CUDA wheels # CUDA wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/AutoGPTQ/releases/download/v0.5.1/auto_gptq-0.5.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
@ -67,14 +67,14 @@ https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/Dao-AILab/flash-attention/releases/download/v2.3.2/flash_attn-2.3.2+cu122torch2.1cxx11abiFALSE-cp38-cp38-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121avx-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121avx-cp38-cp38-win_amd64.whl; platform_system == "Windows" and python_version == "3.8"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121avx-cp311-cp311-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121avx-cp310-cp310-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121avx-cp39-cp39-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.9"
https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.11+cu121avx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8" https://github.com/jllllll/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.18+cu121avx-cp38-cp38-manylinux_2_31_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.8"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9" https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp39-cp39-win_amd64.whl; platform_system == "Windows" and python_version == "3.9"

24
server.py
View File

@ -226,13 +226,19 @@ if __name__ == "__main__":
shared.generation_lock = Lock() shared.generation_lock = Lock()
# Launch the web UI if shared.args.nowebui:
create_interface() # Start the API in standalone mode
while True: shared.args.extensions = [x for x in shared.args.extensions if x != 'gallery']
time.sleep(0.5) if shared.args.extensions is not None and len(shared.args.extensions) > 0:
if shared.need_restart: extensions_module.load_extensions()
shared.need_restart = False else:
# Launch the web UI
create_interface()
while True:
time.sleep(0.5) time.sleep(0.5)
shared.gradio['interface'].close() if shared.need_restart:
time.sleep(0.5) shared.need_restart = False
create_interface() time.sleep(0.5)
shared.gradio['interface'].close()
time.sleep(0.5)
create_interface()