Transformers
fastai
English
Inference Endpoints
experimental / models2.json
sapphomoon's picture
Upload 2 files
6540589
[
{
"order": "a",
"md5sum": "48de9538c774188eb25a7e9ee024bbd3",
"name": "Mistral OpenOrca",
"filename": "mistral-7b-openorca.Q4_0.gguf",
"filesize": "4108927744",
"requires": "2.5.0",
"ramrequired": "8",
"parameters": "7 billion",
"quant": "q4_0",
"type": "Mistral",
"systemPrompt": " ",
"description": "<strong>Best 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.Q4_0.gguf"
},
{
"order": "b",
"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",
"systemPrompt": " ",
"description": "<strong>Best 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>",
"url": "https://gpt4all.io/models/gguf/mistral-7b-instruct-v0.1.Q4_0.gguf",
"promptTemplate": "[INST] %1 [/INST]"
},
{
"order": "c",
"md5sum": "31cb6d527bd3bfb5e73c2e9dfbc75033",
"name": "GPT4All Falcon",
"filename": "gpt4all-falcon-q4_0.gguf",
"filesize": "4210419040",
"requires": "2.5.0",
"ramrequired": "8",
"parameters": "7 billion",
"quant": "q4_0",
"type": "Falcon",
"systemPrompt": " ",
"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-q4_0.gguf",
"promptTemplate": "### Instruction:\n%1\n### Response:\n"
},
{
"order": "e",
"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",
"systemPrompt": " ",
"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"
},
{
"order": "f",
"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",
"systemPrompt": " ",
"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"
},
{
"order": "g",
"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",
"systemPrompt": " ",
"description": "<strong>Best 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>",
"url": "https://gpt4all.io/models/gguf/wizardlm-13b-v1.2.Q4_0.gguf"
},
{
"order": "h",
"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",
"systemPrompt": " ",
"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",
"promptTemplate": "### Instruction:\n%1\n### Response:\n"
},
{
"order": "i",
"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",
"systemPrompt": " ",
"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"
},
{
"order": "j",
"md5sum": "cf5e8f73747f9d7c6fe72a629808c1de",
"name": "MPT Chat",
"filename": "mpt-7b-chat-merges-q4_0.gguf",
"filesize": "3796133728",
"requires": "2.5.0",
"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-merges-q4_0.gguf",
"promptTemplate": "<|im_start|>user\n%1<|im_end|><|im_start|>assistant\n",
"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|>"
},
{
"order": "k",
"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",
"description": "<strong>Small version of new model with novel dataset</strong><br><ul><li>Instruction based<li>Explain tuned datasets<li>Orca Research Paper dataset construction approaches<li>Cannot be used commercially</ul>",
"url": "https://gpt4all.io/models/gguf/orca-mini-3b-gguf2-q4_0.gguf",
"promptTemplate": "### User:\n%1\n### Response:\n",
"systemPrompt": "### System:\nYou are an AI assistant that follows instruction extremely well. Help as much as you can.\n\n"
},
{
"order": "l",
"md5sum": "e30579a1b109882f10e2a5e75ea388fb",
"disableGUI": "true",
"name": "Replit",
"filename": "replit-code-v1_5-3b-q4_0.gguf",
"filesize": "1870449696",
"requires": "2.5.0",
"ramrequired": "4",
"parameters": "3 billion",
"quant": "q4_0",
"type": "Replit",
"systemPrompt": " ",
"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-q4_0.gguf"
},
{
"order": "m",
"md5sum": "556fc3e13df42286997fb58e6f4c639f",
"disableGUI": "true",
"name": "Starcoder",
"filename": "starcoder-q4_0.gguf",
"filesize": "8987166880",
"requires": "2.5.0",
"ramrequired": "4",
"parameters": "7 billion",
"quant": "q4_0",
"type": "Starcoder",
"systemPrompt": " ",
"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-q4_0.gguf"
},
{
"order": "n",
"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",
"systemPrompt": " ",
"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"
},
{
"order": "o",
"md5sum": "e479e6f38b59afc51a470d1953a6bfc7",
"disableGUI": "true",
"name": "SBert",
"filename": "all-MiniLM-L6-v2-f16.gguf",
"filesize": "45887744",
"requires": "2.5.0",
"ramrequired": "1",
"parameters": "40 million",
"quant": "f16",
"type": "Bert",
"systemPrompt": " ",
"description": "<strong>LocalDocs text embeddings model</strong><br><ul><li>Necessary for LocalDocs feature<li>Used for retrieval augmented generation (RAG)",
"url": "https://gpt4all.io/models/gguf/all-MiniLM-L6-v2-f16.gguf"
},
{
"order": "p",
"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. "
}
]