2024-02-21 15:41:20 -05:00
[
{
"order" : "a" ,
2024-04-19 13:09:44 -04:00
"md5sum" : "c87ad09e1e4c8f9c35a5fcef52b6f1c9" ,
2024-07-24 16:32:46 -04:00
"name" : "Llama 3 8B Instruct" ,
2024-04-19 13:09:44 -04:00
"filename" : "Meta-Llama-3-8B-Instruct.Q4_0.gguf" ,
"filesize" : "4661724384" ,
"requires" : "2.7.1" ,
"ramrequired" : "8" ,
"parameters" : "8 billion" ,
"quant" : "q4_0" ,
"type" : "LLaMA3" ,
"description" : "<ul><li>Fast responses</li><li>Chat based model</li><li>Accepts system prompts in Llama 3 format</li><li>Trained by Meta</li><li>License: <a href=\"https://llama.meta.com/llama3/license/\">Meta Llama 3 Community License</a></li></ul>" ,
"url" : "https://gpt4all.io/models/gguf/Meta-Llama-3-8B-Instruct.Q4_0.gguf" ,
"promptTemplate" : "<|start_header_id|>user<|end_header_id|>\n\n%1<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n%2<|eot_id|>" ,
"systemPrompt" : ""
} ,
{
2024-08-19 17:14:33 -04:00
"order" : "b" ,
2024-02-27 09:56:11 -05:00
"md5sum" : "a5f6b4eabd3992da4d7fb7f020f921eb" ,
Add-Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf
Adds Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf, which is the new 7b flagship model of NousResearch.
**Original Model location:**
https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF
**Model description:**
Nous Hermes 2 on Mistral 7B DPO is the new flagship 7B Hermes! This model was DPO'd from Teknium/OpenHermes-2.5-Mistral-7B and has improved across the board on all benchmarks tested - AGIEval, BigBench Reasoning, GPT4All, and TruthfulQA.
The model prior to DPO was trained on 1,000,000 instructions/chats of GPT-4 quality or better, primarily synthetic data as well as other high quality datasets, available from the repository teknium/OpenHermes-2.5.
**Original Dataset Location:**
https://huggingface.co/datasets/teknium/OpenHermes-2.5
**Dataset description:**
This is the dataset that made OpenHermes 2.5 and Nous Hermes 2 series of models.
The Open Hermes 2/2.5 and Nous Hermes 2 models have made significant advancements of SOTA LLM's over recent months, and are underpinned by this exact compilation and curation of many open source datasets and custom created synthetic datasets.
The Open Hermes 2.5 dataset is a continuation of the Open Hermes 1 dataset, at a much larger scale, much more diverse, and much higher quality compilation, reaching 1M, primarily synthetically generated instruction and chat samples.
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
2024-02-25 11:42:03 -05:00
"name" : "Nous Hermes 2 Mistral DPO" ,
"filename" : "Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf" ,
"filesize" : "4108928000" ,
"requires" : "2.7.1" ,
"ramrequired" : "8" ,
"parameters" : "7 billion" ,
"quant" : "q4_0" ,
"type" : "Mistral" ,
2024-07-24 16:32:46 -04:00
"description" : "<strong>Good overall fast chat model</strong><br><ul><li>Fast responses</li><li>Chat based model</li><li>Accepts system prompts in ChatML format</li><li>Trained by Mistral AI<li>Finetuned by Nous Research on the OpenHermes-2.5 dataset<li>Licensed for commercial use</ul>" ,
2024-02-27 09:34:50 -05:00
"url" : "https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF/resolve/main/Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf" ,
Add-Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf
Adds Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf, which is the new 7b flagship model of NousResearch.
**Original Model location:**
https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF
**Model description:**
Nous Hermes 2 on Mistral 7B DPO is the new flagship 7B Hermes! This model was DPO'd from Teknium/OpenHermes-2.5-Mistral-7B and has improved across the board on all benchmarks tested - AGIEval, BigBench Reasoning, GPT4All, and TruthfulQA.
The model prior to DPO was trained on 1,000,000 instructions/chats of GPT-4 quality or better, primarily synthetic data as well as other high quality datasets, available from the repository teknium/OpenHermes-2.5.
**Original Dataset Location:**
https://huggingface.co/datasets/teknium/OpenHermes-2.5
**Dataset description:**
This is the dataset that made OpenHermes 2.5 and Nous Hermes 2 series of models.
The Open Hermes 2/2.5 and Nous Hermes 2 models have made significant advancements of SOTA LLM's over recent months, and are underpinned by this exact compilation and curation of many open source datasets and custom created synthetic datasets.
The Open Hermes 2.5 dataset is a continuation of the Open Hermes 1 dataset, at a much larger scale, much more diverse, and much higher quality compilation, reaching 1M, primarily synthetically generated instruction and chat samples.
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
2024-02-25 11:42:03 -05:00
"promptTemplate" : "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n%2<|im_end|>\n" ,
2024-03-01 14:19:18 -05:00
"systemPrompt" : ""
Add-Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf
Adds Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf, which is the new 7b flagship model of NousResearch.
**Original Model location:**
https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF
**Model description:**
Nous Hermes 2 on Mistral 7B DPO is the new flagship 7B Hermes! This model was DPO'd from Teknium/OpenHermes-2.5-Mistral-7B and has improved across the board on all benchmarks tested - AGIEval, BigBench Reasoning, GPT4All, and TruthfulQA.
The model prior to DPO was trained on 1,000,000 instructions/chats of GPT-4 quality or better, primarily synthetic data as well as other high quality datasets, available from the repository teknium/OpenHermes-2.5.
**Original Dataset Location:**
https://huggingface.co/datasets/teknium/OpenHermes-2.5
**Dataset description:**
This is the dataset that made OpenHermes 2.5 and Nous Hermes 2 series of models.
The Open Hermes 2/2.5 and Nous Hermes 2 models have made significant advancements of SOTA LLM's over recent months, and are underpinned by this exact compilation and curation of many open source datasets and custom created synthetic datasets.
The Open Hermes 2.5 dataset is a continuation of the Open Hermes 1 dataset, at a much larger scale, much more diverse, and much higher quality compilation, reaching 1M, primarily synthetically generated instruction and chat samples.
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
2024-02-25 11:42:03 -05:00
} ,
2024-02-21 16:18:26 -05:00
{
2024-08-19 17:14:33 -04:00
"order" : "c" ,
2024-02-21 16:18:26 -05:00
"md5sum" : "97463be739b50525df56d33b26b00852" ,
"name" : "Mistral Instruct" ,
"filename" : "mistral-7b-instruct-v0.1.Q4_0.gguf" ,
"filesize" : "4108916384" ,
"requires" : "2.5.0" ,
"ramrequired" : "8" ,
"parameters" : "7 billion" ,
"quant" : "q4_0" ,
"type" : "Mistral" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "" ,
Add-Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf
Adds Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf, which is the new 7b flagship model of NousResearch.
**Original Model location:**
https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF
**Model description:**
Nous Hermes 2 on Mistral 7B DPO is the new flagship 7B Hermes! This model was DPO'd from Teknium/OpenHermes-2.5-Mistral-7B and has improved across the board on all benchmarks tested - AGIEval, BigBench Reasoning, GPT4All, and TruthfulQA.
The model prior to DPO was trained on 1,000,000 instructions/chats of GPT-4 quality or better, primarily synthetic data as well as other high quality datasets, available from the repository teknium/OpenHermes-2.5.
**Original Dataset Location:**
https://huggingface.co/datasets/teknium/OpenHermes-2.5
**Dataset description:**
This is the dataset that made OpenHermes 2.5 and Nous Hermes 2 series of models.
The Open Hermes 2/2.5 and Nous Hermes 2 models have made significant advancements of SOTA LLM's over recent months, and are underpinned by this exact compilation and curation of many open source datasets and custom created synthetic datasets.
The Open Hermes 2.5 dataset is a continuation of the Open Hermes 1 dataset, at a much larger scale, much more diverse, and much higher quality compilation, reaching 1M, primarily synthetically generated instruction and chat samples.
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
2024-02-25 11:42:03 -05:00
"description" : "<strong>Strong overall fast instruction following model</strong><br><ul><li>Fast responses</li><li>Trained by Mistral AI<li>Uncensored</li><li>Licensed for commercial use</li></ul>" ,
2024-02-21 16:18:26 -05:00
"url" : "https://gpt4all.io/models/gguf/mistral-7b-instruct-v0.1.Q4_0.gguf" ,
"promptTemplate" : "[INST] %1 [/INST]"
} ,
2024-08-19 17:14:33 -04:00
{
"order" : "d" ,
"md5sum" : "8a9c75bcd8a66b7693f158ec96924eeb" ,
"name" : "Llama 3.1 8B Instruct 128k" ,
"filename" : "Meta-Llama-3.1-8B-Instruct-128k-Q4_0.gguf" ,
"filesize" : "4661212096" ,
"requires" : "3.1.1" ,
"ramrequired" : "8" ,
"parameters" : "8 billion" ,
"quant" : "q4_0" ,
"type" : "LLaMA3" ,
"description" : "<ul><li><strong>For advanced users only. Not recommended for use on Windows or Linux without selecting CUDA due to speed issues.</strong></li><li>Fast responses</li><li>Chat based model</li><li>Large context size of 128k</li><li>Accepts agentic system prompts in Llama 3.1 format</li><li>Trained by Meta</li><li>License: <a href=\"https://llama.meta.com/llama3_1/license/\">Meta Llama 3.1 Community License</a></li></ul>" ,
"url" : "https://huggingface.co/GPT4All-Community/Meta-Llama-3.1-8B-Instruct-128k/resolve/main/Meta-Llama-3.1-8B-Instruct-128k-Q4_0.gguf" ,
"promptTemplate" : "<|start_header_id|>user<|end_header_id|>\n\n%1<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n%2" ,
"systemPrompt" : "<|start_header_id|>system<|end_header_id|>\nCutting Knowledge Date: December 2023\n\nYou are a helpful assistant.<|eot_id|>"
} ,
2024-02-21 15:41:20 -05:00
{
2024-07-24 16:32:46 -04:00
"order" : "e" ,
2024-04-19 13:09:44 -04:00
"md5sum" : "f692417a22405d80573ac10cb0cd6c6a" ,
"name" : "Mistral OpenOrca" ,
"filename" : "mistral-7b-openorca.gguf2.Q4_0.gguf" ,
"filesize" : "4108928128" ,
"requires" : "2.7.1" ,
"ramrequired" : "8" ,
"parameters" : "7 billion" ,
"quant" : "q4_0" ,
"type" : "Mistral" ,
"description" : "<strong>Strong overall fast chat model</strong><br><ul><li>Fast responses</li><li>Chat based model</li><li>Trained by Mistral AI<li>Finetuned on OpenOrca dataset curated via <a href=\"https://atlas.nomic.ai/\">Nomic Atlas</a><li>Licensed for commercial use</ul>" ,
"url" : "https://gpt4all.io/models/gguf/mistral-7b-openorca.gguf2.Q4_0.gguf" ,
"promptTemplate" : "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n%2<|im_end|>\n" ,
"systemPrompt" : "<|im_start|>system\nYou are MistralOrca, a large language model trained by Alignment Lab AI.\n<|im_end|>\n"
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "f" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "c4c78adf744d6a20f05c8751e3961b84" ,
"name" : "GPT4All Falcon" ,
"filename" : "gpt4all-falcon-newbpe-q4_0.gguf" ,
"filesize" : "4210994112" ,
"requires" : "2.6.0" ,
"ramrequired" : "8" ,
"parameters" : "7 billion" ,
"quant" : "q4_0" ,
"type" : "Falcon" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "" ,
2024-02-21 15:41:20 -05:00
"description" : "<strong>Very fast model with good quality</strong><br><ul><li>Fastest responses</li><li>Instruction based</li><li>Trained by TII<li>Finetuned by Nomic AI<li>Licensed for commercial use</ul>" ,
"url" : "https://gpt4all.io/models/gguf/gpt4all-falcon-newbpe-q4_0.gguf" ,
2024-02-26 13:11:15 -05:00
"promptTemplate" : "### Instruction:\n%1\n\n### Response:\n"
2024-02-21 15:41:20 -05:00
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "g" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "00c8593ba57f5240f59662367b3ed4a5" ,
"name" : "Orca 2 (Medium)" ,
"filename" : "orca-2-7b.Q4_0.gguf" ,
"filesize" : "3825824192" ,
"requires" : "2.5.2" ,
"ramrequired" : "8" ,
"parameters" : "7 billion" ,
"quant" : "q4_0" ,
"type" : "LLaMA2" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "" ,
2024-02-21 15:41:20 -05:00
"description" : "<ul><li>Instruction based<li>Trained by Microsoft<li>Cannot be used commercially</ul>" ,
"url" : "https://gpt4all.io/models/gguf/orca-2-7b.Q4_0.gguf"
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "h" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "3c0d63c4689b9af7baa82469a6f51a19" ,
"name" : "Orca 2 (Full)" ,
"filename" : "orca-2-13b.Q4_0.gguf" ,
"filesize" : "7365856064" ,
"requires" : "2.5.2" ,
"ramrequired" : "16" ,
"parameters" : "13 billion" ,
"quant" : "q4_0" ,
"type" : "LLaMA2" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "" ,
2024-02-21 15:41:20 -05:00
"description" : "<ul><li>Instruction based<li>Trained by Microsoft<li>Cannot be used commercially</ul>" ,
"url" : "https://gpt4all.io/models/gguf/orca-2-13b.Q4_0.gguf"
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "i" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "5aff90007499bce5c64b1c0760c0b186" ,
"name" : "Wizard v1.2" ,
"filename" : "wizardlm-13b-v1.2.Q4_0.gguf" ,
"filesize" : "7365834624" ,
"requires" : "2.5.0" ,
"ramrequired" : "16" ,
"parameters" : "13 billion" ,
"quant" : "q4_0" ,
"type" : "LLaMA2" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "" ,
Add-Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf
Adds Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf, which is the new 7b flagship model of NousResearch.
**Original Model location:**
https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF
**Model description:**
Nous Hermes 2 on Mistral 7B DPO is the new flagship 7B Hermes! This model was DPO'd from Teknium/OpenHermes-2.5-Mistral-7B and has improved across the board on all benchmarks tested - AGIEval, BigBench Reasoning, GPT4All, and TruthfulQA.
The model prior to DPO was trained on 1,000,000 instructions/chats of GPT-4 quality or better, primarily synthetic data as well as other high quality datasets, available from the repository teknium/OpenHermes-2.5.
**Original Dataset Location:**
https://huggingface.co/datasets/teknium/OpenHermes-2.5
**Dataset description:**
This is the dataset that made OpenHermes 2.5 and Nous Hermes 2 series of models.
The Open Hermes 2/2.5 and Nous Hermes 2 models have made significant advancements of SOTA LLM's over recent months, and are underpinned by this exact compilation and curation of many open source datasets and custom created synthetic datasets.
The Open Hermes 2.5 dataset is a continuation of the Open Hermes 1 dataset, at a much larger scale, much more diverse, and much higher quality compilation, reaching 1M, primarily synthetically generated instruction and chat samples.
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
2024-02-25 11:42:03 -05:00
"description" : "<strong>Strong overall larger model</strong><br><ul><li>Instruction based<li>Gives very long responses<li>Finetuned with only 1k of high-quality data<li>Trained by Microsoft and Peking University<li>Cannot be used commercially</ul>" ,
2024-02-21 15:41:20 -05:00
"url" : "https://gpt4all.io/models/gguf/wizardlm-13b-v1.2.Q4_0.gguf"
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "j" ,
2024-04-19 13:09:44 -04:00
"md5sum" : "31b47b4e8c1816b62684ac3ca373f9e1" ,
"name" : "Ghost 7B v0.9.1" ,
"filename" : "ghost-7b-v0.9.1-Q4_0.gguf" ,
"filesize" : "4108916960" ,
"requires" : "2.7.1" ,
"ramrequired" : "8" ,
"parameters" : "7 billion" ,
"quant" : "q4_0" ,
"type" : "Mistral" ,
"description" : "<strong>Ghost 7B v0.9.1</strong> fast, powerful and smooth for Vietnamese and English languages." ,
"url" : "https://huggingface.co/lamhieu/ghost-7b-v0.9.1-gguf/resolve/main/ghost-7b-v0.9.1-Q4_0.gguf" ,
"promptTemplate" : "<|user|>\n%1</s>\n<|assistant|>\n%2</s>\n" ,
"systemPrompt" : "<|system|>\nYou are Ghost created by Lam Hieu. You are a helpful and knowledgeable assistant. You like to help and always give honest information, in its original language. In communication, you are always respectful, equal and promote positive behavior.\n</s>"
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "k" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "3d12810391d04d1153b692626c0c6e16" ,
"name" : "Hermes" ,
"filename" : "nous-hermes-llama2-13b.Q4_0.gguf" ,
"filesize" : "7366062080" ,
"requires" : "2.5.0" ,
"ramrequired" : "16" ,
"parameters" : "13 billion" ,
"quant" : "q4_0" ,
"type" : "LLaMA2" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "" ,
2024-02-21 15:41:20 -05:00
"description" : "<strong>Extremely good model</strong><br><ul><li>Instruction based<li>Gives long responses<li>Curated with 300,000 uncensored instructions<li>Trained by Nous Research<li>Cannot be used commercially</ul>" ,
"url" : "https://gpt4all.io/models/gguf/nous-hermes-llama2-13b.Q4_0.gguf" ,
2024-02-26 13:11:15 -05:00
"promptTemplate" : "### Instruction:\n%1\n\n### Response:\n"
2024-02-21 15:41:20 -05:00
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "l" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "40388eb2f8d16bb5d08c96fdfaac6b2c" ,
"name" : "Snoozy" ,
"filename" : "gpt4all-13b-snoozy-q4_0.gguf" ,
"filesize" : "7365834624" ,
"requires" : "2.5.0" ,
"ramrequired" : "16" ,
"parameters" : "13 billion" ,
"quant" : "q4_0" ,
"type" : "LLaMA" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "" ,
2024-02-21 15:41:20 -05:00
"description" : "<strong>Very good overall model</strong><br><ul><li>Instruction based<li>Based on the same dataset as Groovy<li>Slower than Groovy, with higher quality responses<li>Trained by Nomic AI<li>Cannot be used commercially</ul>" ,
"url" : "https://gpt4all.io/models/gguf/gpt4all-13b-snoozy-q4_0.gguf"
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "m" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "15dcb4d7ea6de322756449c11a0b7545" ,
"name" : "MPT Chat" ,
"filename" : "mpt-7b-chat-newbpe-q4_0.gguf" ,
"filesize" : "3912373472" ,
2024-04-19 13:09:44 -04:00
"requires" : "2.7.1" ,
2024-03-08 17:18:38 -05:00
"removedIn" : "2.7.3" ,
2024-02-21 15:41:20 -05:00
"ramrequired" : "8" ,
"parameters" : "7 billion" ,
"quant" : "q4_0" ,
"type" : "MPT" ,
"description" : "<strong>Good model with novel architecture</strong><br><ul><li>Fast responses<li>Chat based<li>Trained by Mosaic ML<li>Cannot be used commercially</ul>" ,
"url" : "https://gpt4all.io/models/gguf/mpt-7b-chat-newbpe-q4_0.gguf" ,
"promptTemplate" : "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n%2<|im_end|>\n" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "<|im_start|>system\n- You are a helpful assistant chatbot trained by MosaicML.\n- You answer questions.\n- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.\n- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>\n"
2024-03-08 17:18:38 -05:00
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "n" ,
2024-03-08 17:18:38 -05:00
"md5sum" : "ab5d8e8a2f79365ea803c1f1d0aa749d" ,
"name" : "MPT Chat" ,
"filename" : "mpt-7b-chat.gguf4.Q4_0.gguf" ,
"filesize" : "3796178112" ,
"requires" : "2.7.3" ,
"ramrequired" : "8" ,
"parameters" : "7 billion" ,
"quant" : "q4_0" ,
"type" : "MPT" ,
"description" : "<strong>Good model with novel architecture</strong><br><ul><li>Fast responses<li>Chat based<li>Trained by Mosaic ML<li>Cannot be used commercially</ul>" ,
"url" : "https://gpt4all.io/models/gguf/mpt-7b-chat.gguf4.Q4_0.gguf" ,
"promptTemplate" : "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n%2<|im_end|>\n" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "<|im_start|>system\n- You are a helpful assistant chatbot trained by MosaicML.\n- You answer questions.\n- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.\n- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>\n"
2024-02-21 15:41:20 -05:00
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "o" ,
2024-04-23 18:53:09 -04:00
"md5sum" : "f8347badde9bfc2efbe89124d78ddaf5" ,
"name" : "Phi-3 Mini Instruct" ,
"filename" : "Phi-3-mini-4k-instruct.Q4_0.gguf" ,
"filesize" : "2176181568" ,
"requires" : "2.7.1" ,
"ramrequired" : "4" ,
"parameters" : "4 billion" ,
"quant" : "q4_0" ,
"type" : "Phi-3" ,
"description" : "<ul><li>Very fast responses</li><li>Chat based model</li><li>Accepts system prompts in Phi-3 format</li><li>Trained by Microsoft</li><li>License: <a href=\"https://opensource.org/license/mit\">MIT</a></li><li>No restrictions on commercial use</li></ul>" ,
"url" : "https://gpt4all.io/models/gguf/Phi-3-mini-4k-instruct.Q4_0.gguf" ,
"promptTemplate" : "<|user|>\n%1<|end|>\n<|assistant|>\n%2<|end|>\n" ,
"systemPrompt" : ""
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "p" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "0e769317b90ac30d6e09486d61fefa26" ,
"name" : "Mini Orca (Small)" ,
"filename" : "orca-mini-3b-gguf2-q4_0.gguf" ,
"filesize" : "1979946720" ,
"requires" : "2.5.0" ,
"ramrequired" : "4" ,
"parameters" : "3 billion" ,
"quant" : "q4_0" ,
"type" : "OpenLLaMa" ,
2024-04-23 18:53:09 -04:00
"description" : "<strong>Small version of new model with novel dataset</strong><br><ul><li>Very fast responses</li><li>Instruction based</li><li>Explain tuned datasets</li><li>Orca Research Paper dataset construction approaches</li><li>Cannot be used commercially</li></ul>" ,
2024-02-21 15:41:20 -05:00
"url" : "https://gpt4all.io/models/gguf/orca-mini-3b-gguf2-q4_0.gguf" ,
2024-02-26 13:11:15 -05:00
"promptTemplate" : "### User:\n%1\n\n### Response:\n" ,
2024-02-21 15:41:20 -05:00
"systemPrompt" : "### System:\nYou are an AI assistant that follows instruction extremely well. Help as much as you can.\n\n"
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "q" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "c232f17e09bca4b7ee0b5b1f4107c01e" ,
"disableGUI" : "true" ,
"name" : "Replit" ,
"filename" : "replit-code-v1_5-3b-newbpe-q4_0.gguf" ,
"filesize" : "1953055104" ,
"requires" : "2.6.0" ,
"ramrequired" : "4" ,
"parameters" : "3 billion" ,
"quant" : "q4_0" ,
"type" : "Replit" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "" ,
2024-02-21 15:41:20 -05:00
"promptTemplate" : "%1" ,
"description" : "<strong>Trained on subset of the Stack</strong><br><ul><li>Code completion based<li>Licensed for commercial use<li>WARNING: Not available for chat GUI</ul>" ,
"url" : "https://gpt4all.io/models/gguf/replit-code-v1_5-3b-newbpe-q4_0.gguf"
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "r" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "70841751ccd95526d3dcfa829e11cd4c" ,
"disableGUI" : "true" ,
"name" : "Starcoder" ,
"filename" : "starcoder-newbpe-q4_0.gguf" ,
"filesize" : "8987411904" ,
"requires" : "2.6.0" ,
"ramrequired" : "4" ,
"parameters" : "7 billion" ,
"quant" : "q4_0" ,
"type" : "Starcoder" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "" ,
2024-02-21 15:41:20 -05:00
"promptTemplate" : "%1" ,
"description" : "<strong>Trained on subset of the Stack</strong><br><ul><li>Code completion based<li>WARNING: Not available for chat GUI</ul>" ,
"url" : "https://gpt4all.io/models/gguf/starcoder-newbpe-q4_0.gguf"
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "s" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "e973dd26f0ffa6e46783feaea8f08c83" ,
"disableGUI" : "true" ,
"name" : "Rift coder" ,
"filename" : "rift-coder-v0-7b-q4_0.gguf" ,
"filesize" : "3825903776" ,
"requires" : "2.5.0" ,
"ramrequired" : "8" ,
"parameters" : "7 billion" ,
"quant" : "q4_0" ,
"type" : "LLaMA" ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "" ,
2024-02-21 15:41:20 -05:00
"promptTemplate" : "%1" ,
"description" : "<strong>Trained on collection of Python and TypeScript</strong><br><ul><li>Code completion based<li>WARNING: Not available for chat GUI</li>" ,
"url" : "https://gpt4all.io/models/gguf/rift-coder-v0-7b-q4_0.gguf"
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "t" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "e479e6f38b59afc51a470d1953a6bfc7" ,
"disableGUI" : "true" ,
"name" : "SBert" ,
"filename" : "all-MiniLM-L6-v2-f16.gguf" ,
"filesize" : "45887744" ,
"requires" : "2.5.0" ,
2024-03-13 18:09:24 -04:00
"removedIn" : "2.7.4" ,
2024-02-21 15:41:20 -05:00
"ramrequired" : "1" ,
"parameters" : "40 million" ,
"quant" : "f16" ,
"type" : "Bert" ,
2024-03-13 18:09:24 -04:00
"embeddingModel" : true ,
2024-03-15 11:49:58 -04:00
"systemPrompt" : "" ,
2024-02-21 15:41:20 -05:00
"description" : "<strong>LocalDocs text embeddings model</strong><br><ul><li>For use with LocalDocs feature<li>Used for retrieval augmented generation (RAG)" ,
"url" : "https://gpt4all.io/models/gguf/all-MiniLM-L6-v2-f16.gguf"
} ,
2024-03-13 18:09:24 -04:00
{
2024-07-24 16:32:46 -04:00
"order" : "u" ,
2024-03-13 18:09:24 -04:00
"md5sum" : "dd90e2cb7f8e9316ac3796cece9883b5" ,
"name" : "SBert" ,
"filename" : "all-MiniLM-L6-v2.gguf2.f16.gguf" ,
"filesize" : "45949216" ,
"requires" : "2.7.4" ,
2024-06-28 20:34:03 -04:00
"removedIn" : "3.0.0" ,
2024-03-13 18:09:24 -04:00
"ramrequired" : "1" ,
"parameters" : "40 million" ,
"quant" : "f16" ,
"type" : "Bert" ,
"embeddingModel" : true ,
"description" : "<strong>LocalDocs text embeddings model</strong><br><ul><li>For use with LocalDocs feature<li>Used for retrieval augmented generation (RAG)" ,
"url" : "https://gpt4all.io/models/gguf/all-MiniLM-L6-v2.gguf2.f16.gguf"
} ,
2024-02-21 15:41:20 -05:00
{
2024-07-24 16:32:46 -04:00
"order" : "v" ,
2024-02-21 15:41:20 -05:00
"md5sum" : "919de4dd6f25351bcb0223790db1932d" ,
"name" : "EM German Mistral" ,
"filename" : "em_german_mistral_v01.Q4_0.gguf" ,
"filesize" : "4108916352" ,
"requires" : "2.5.0" ,
"ramrequired" : "8" ,
"parameters" : "7 billion" ,
"quant" : "q4_0" ,
"type" : "Mistral" ,
"description" : "<strong>Mistral-based model for German-language applications</strong><br><ul><li>Fast responses</li><li>Chat based model</li><li>Trained by ellamind<li>Finetuned on German instruction and chat data</a><li>Licensed for commercial use</ul>" ,
"url" : "https://huggingface.co/TheBloke/em_german_mistral_v01-GGUF/resolve/main/em_german_mistral_v01.Q4_0.gguf" ,
"promptTemplate" : "USER: %1 ASSISTANT: " ,
"systemPrompt" : "Du bist ein hilfreicher Assistent. "
2024-03-13 18:09:24 -04:00
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "w" ,
2024-03-13 18:09:24 -04:00
"md5sum" : "60ea031126f82db8ddbbfecc668315d2" ,
"disableGUI" : "true" ,
"name" : "Nomic Embed Text v1" ,
"filename" : "nomic-embed-text-v1.f16.gguf" ,
"filesize" : "274290560" ,
"requires" : "2.7.4" ,
"ramrequired" : "1" ,
"parameters" : "137 million" ,
"quant" : "f16" ,
"type" : "Bert" ,
"embeddingModel" : true ,
"systemPrompt" : "" ,
"description" : "nomic-embed-text-v1" ,
"url" : "https://gpt4all.io/models/gguf/nomic-embed-text-v1.f16.gguf"
} ,
{
2024-07-24 16:32:46 -04:00
"order" : "x" ,
2024-03-13 18:09:24 -04:00
"md5sum" : "a5401e7f7e46ed9fcaed5b60a281d547" ,
"disableGUI" : "true" ,
"name" : "Nomic Embed Text v1.5" ,
"filename" : "nomic-embed-text-v1.5.f16.gguf" ,
"filesize" : "274290560" ,
"requires" : "2.7.4" ,
"ramrequired" : "1" ,
"parameters" : "137 million" ,
"quant" : "f16" ,
"type" : "Bert" ,
"embeddingModel" : true ,
"systemPrompt" : "" ,
"description" : "nomic-embed-text-v1.5" ,
"url" : "https://gpt4all.io/models/gguf/nomic-embed-text-v1.5.f16.gguf"
2024-07-29 09:57:33 -04:00
} ,
{
"order" : "z" ,
"md5sum" : "a8c5a783105f87a481543d4ed7d7586d" ,
"name" : "Qwen2-1.5B-Instruct" ,
"filename" : "qwen2-1_5b-instruct-q4_0.gguf" ,
"filesize" : "937532800" ,
"requires" : "3.0" ,
"ramrequired" : "4" ,
"parameters" : "1.5 billion" ,
"quant" : "q4_0" ,
"type" : "qwen2" ,
"description" : "<ul><li>Very fast responses</li><li>Instruction based model</li><li>Usage of LocalDocs (RAG): Highly recommended</li><li>Supports context length of up to 32768</li><li>Trained and finetuned by Qwen (Alibaba Cloud)</li><li>License: <a href=\"https://www.apache.org/licenses/LICENSE-2.0.html/\">Apache 2.0</a></li></ul>" ,
"url" : "https://huggingface.co/Qwen/Qwen2-1.5B-Instruct-GGUF/resolve/main/qwen2-1_5b-instruct-q4_0.gguf" ,
"promptTemplate" : "<|im_start|>user\n%1<|im_end|>\n<|im_start|>assistant\n%2<|im_end|>" ,
"systemPrompt" : "<|im_start|>system\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.<|im_end|>\n"
2024-02-21 15:41:20 -05:00
}
]
