Update Model.json (#1005)
* add(mixtral): add model.json for mixtral * archived some models + update the model.json * add(model): add pandora 10.7b * fix(model): update description * fix(model): pump vers and change the featured model to trinity * fix(model): archive neuralchat * fix(model): decapriated all old models * fix(trinity): add cover image and change description * fix(trinity): update cover png * add(pandora): cover image * fix(pandora): cover image * add(mixtral): add model.json for mixtral * archived some models + update the model.json * add(model): add pandora 10.7b * fix(model): update description * fix(model): pump vers and change the featured model to trinity * fix(model): archive neuralchat * fix(model): decapriated all old models * fix(trinity): add cover image and change description * fix(trinity): update cover png * add(pandora): cover image * fix(pandora): cover image * chore: model desc nits * fix(models): adjust the size for solars and pandoras * add(mixtral): description --------- Co-authored-by: 0xSage <n@pragmatic.vc>
This commit is contained in:
Hoang Ha
GitHub
parent
cf7e9350b7
commit
ecc866427b
@ -1,23 +0,0 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_M.gguf",
|
||||
"id": "llama2-chat-7b-q5",
|
||||
"object": "model",
|
||||
"name": "Llama 2 Chat 7B Q5",
|
||||
"version": "1.0",
|
||||
"description": "This is a 5-bit quantized iteration of Meta AI's Llama 2 Chat 7b model, specifically designed for a comprehensive understanding through training on extensive internet data.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 2048,
|
||||
"prompt_template": "[INST] <<SYS>>\n{system_message}<</SYS>>\n{prompt}[/INST]"
|
||||
},
|
||||
"parameters": {
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "MetaAI, The Bloke",
|
||||
"tags": ["7B", "Foundational Model"],
|
||||
"size": 4780000000
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
|
||||
@ -1,23 +0,0 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q5_K_M.gguf",
|
||||
"id": "mistral-ins-7b-q5",
|
||||
"object": "model",
|
||||
"name": "Mistral Instruct 7B Q5",
|
||||
"version": "1.0",
|
||||
"description": "This is a 5-bit quantized iteration of MistralAI's Mistral Instruct 7b model, specifically designed for a comprehensive understanding through training on extensive internet data.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 2048,
|
||||
"prompt_template": "<s>[INST]{prompt}\n[/INST]"
|
||||
},
|
||||
"parameters": {
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "MistralAI, The Bloke",
|
||||
"tags": ["7B", "Foundational Model"],
|
||||
"size": 5130000000
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
|
||||
22
models/mixtral-8x7b-instruct/model.json
Normal file
22
models/mixtral-8x7b-instruct/model.json
Normal file
@ -0,0 +1,22 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/resolve/main/mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf",
|
||||
"id": "mixtral-8x7b-instruct",
|
||||
"object": "model",
|
||||
"name": "Mixtral 8x7B Instruct Q4",
|
||||
"version": "1.0",
|
||||
"description": "The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 2048,
|
||||
"prompt_template": "[INST] {prompt} [/INST]"
|
||||
},
|
||||
"parameters": {
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "MistralAI, TheBloke",
|
||||
"tags": ["MOE", "Foundational Model"],
|
||||
"size": 26440000000
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
@ -1,23 +0,0 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/TheBloke/neural-chat-7B-v3-1-GGUF/resolve/main/neural-chat-7b-v3-1.Q4_K_M.gguf",
|
||||
"id": "neural-chat-7b",
|
||||
"object": "model",
|
||||
"name": "Neural Chat 7B Q4",
|
||||
"version": "1.0",
|
||||
"description": "The Neural Chat 7B model, developed on the foundation of mistralai/Mistral-7B-v0.1, has been fine-tuned using the Open-Orca/SlimOrca dataset and aligned with the Direct Preference Optimization (DPO) algorithm. It has demonstrated substantial improvements in various AI tasks and performance well on the open_llm_leaderboard.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 2048,
|
||||
"prompt_template": "### System:\n{system_message}### User:\n{prompt}### Assistant:"
|
||||
},
|
||||
"parameters": {
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "Intel, The Bloke",
|
||||
"tags": ["Recommended", "7B", "Finetuned"],
|
||||
"size": 4370000000
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 3.9 MiB |
@ -1,10 +1,10 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-7B-v3-1-7B-GGUF/resolve/main/openhermes-2.5-neural-chat-7b-v3-1-7b.Q4_K_M.gguf",
|
||||
"source_url": "https://huggingface.co/janhq/openhermes-2.5-neural-chat-v3-3-slerp-GGUF/resolve/main/openhermes-2.5-neural-chat-v3-3-slerp.Q4_K_M.gguf",
|
||||
"id": "openhermes-neural-7b",
|
||||
"object": "model",
|
||||
"name": "OpenHermes Neural 7B Q4",
|
||||
"version": "1.0",
|
||||
"description": "OpenHermes Neural is a merged model from OpenHermes-2.5-Mistral-7B and neural-chat-7b-v3-1 with the TIES method.",
|
||||
"description": "OpenHermes Neural is a merged model using the TIES method.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 2048,
|
||||
@ -14,10 +14,9 @@
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "Intel, The Bloke",
|
||||
"tags": ["Featured", "7B", "Merged"],
|
||||
"size": 4370000000,
|
||||
"cover": "https://raw.githubusercontent.com/janhq/jan/main/models/openhermes-neural-7b/cover.png"
|
||||
"author": "Intel, Jan",
|
||||
"tags": ["7B", "Merged"],
|
||||
"size": 4370000000
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
|
||||
@ -1,23 +0,0 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/TheBloke/Orca-2-13B-GGUF/resolve/main/orca-2-13b.Q5_K_M.gguf",
|
||||
"id": "openorca-13b",
|
||||
"object": "model",
|
||||
"name": "Orca 2 13B Q5",
|
||||
"version": "1.0",
|
||||
"description": "Orca 2 is a finetuned version of LLAMA-2, designed primarily for single-turn responses in reasoning, reading comprehension, math problem solving, and text summarization.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 2048,
|
||||
"prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
|
||||
},
|
||||
"parameters": {
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "Microsoft, The Bloke",
|
||||
"tags": ["13B", "Finetuned"],
|
||||
"size": 9230000000
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
|
||||
BIN
models/pandora-10.7b-v1/cover.png
Normal file
BIN
models/pandora-10.7b-v1/cover.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.3 MiB |
24
models/pandora-10.7b-v1/model.json
Normal file
24
models/pandora-10.7b-v1/model.json
Normal file
@ -0,0 +1,24 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/janhq/pandora-v1-10.7b-GGUF/resolve/main/pandora-v1-10.7b.Q4_K_M.gguf",
|
||||
"id": "pandora-10.7b-v1",
|
||||
"object": "model",
|
||||
"name": "Pandora 11B Q4",
|
||||
"version": "1.0",
|
||||
"description": "Pandora, our research model, employs the Passthrough merging technique to merge 2x7B models into 1.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 2048,
|
||||
"prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
|
||||
},
|
||||
"parameters": {
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "Jan",
|
||||
"tags": ["11B","Finetuned", "Featured"],
|
||||
"size": 6360000000,
|
||||
"cover": "https://raw.githubusercontent.com/janhq/jan/main/models/pandora-10.7b-v1/cover.png"
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
|
||||
@ -1,22 +0,0 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/TheBloke/rocket-3B-GGUF/resolve/main/rocket-3b.Q4_K_M.gguf",
|
||||
"id": "rocket-3b",
|
||||
"object": "model",
|
||||
"name": "Rocket 3B Q4",
|
||||
"version": "1.0",
|
||||
"description": "Rocket-3B is a GPT-like model, primarily English, fine-tuned on diverse public datasets. It outperforms larger models in benchmarks, showcasing superior understanding and text generation, making it an effective chat model for its size.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 4096,
|
||||
"prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
|
||||
},
|
||||
"parameters": {
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "Pansophic, The Bloke",
|
||||
"tags": ["Tiny", "Finetuned"],
|
||||
"size": 1710000000
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
23
models/solar-10.7b-instruct/model.json
Normal file
23
models/solar-10.7b-instruct/model.json
Normal file
@ -0,0 +1,23 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/janhq/Solar-10.7B-Instruct-v1.0/resolve/main/solar-10.7b-instruct-v1.0.Q4_K_M.gguf",
|
||||
"id": "solar-10.7b-instruct",
|
||||
"object": "model",
|
||||
"name": "Solar Instruct 10.7B Q4",
|
||||
"version": "1.0",
|
||||
"description": "SOLAR-10.7B model built on the Llama2 architecture with Depth Up-Scaling and integrated Mistral 7B weights. Its robustness and adaptability make it ideal for fine-tuning applications, significantly enhancing performance with simple instruction-based techniques.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 2048,
|
||||
"prompt_template": "### User: {prompt}\n### Assistant:"
|
||||
},
|
||||
"parameters": {
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "Upstage, Jan",
|
||||
"tags": ["11B","Finetuned"],
|
||||
"size": 6360000000
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
|
||||
0
models/solar-10.7b-slerp/model.json
Normal file
0
models/solar-10.7b-slerp/model.json
Normal file
@ -1,23 +0,0 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/TheBloke/LLaMA2-13B-Tiefighter-GGUF/resolve/main/llama2-13b-tiefighter.Q5_K_M.gguf",
|
||||
"id": "tiefighter-13b",
|
||||
"object": "model",
|
||||
"name": "Tiefighter 13B Q5",
|
||||
"version": "1.0",
|
||||
"description": "Tiefighter-13B is a highly creative, merged AI model achieved by combining various 'LORAs' on top of an existing merge, particularly focusing on storytelling and improvisation. This model excels in story writing, chatbots, and adventuring, and is designed to perform better with less detailed inputs, leveraging its inherent creativity.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 2048,
|
||||
"prompt_template": "### Instruction:\n{prompt}\n### Response:"
|
||||
},
|
||||
"parameters": {
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "KoboldAI, The Bloke",
|
||||
"tags": ["13B", "Finetuned"],
|
||||
"size": 9230000000
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
|
||||
BIN
models/trinity-v1-7b/cover.png
Normal file
BIN
models/trinity-v1-7b/cover.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.7 MiB |
23
models/trinity-v1-7b/model.json
Normal file
23
models/trinity-v1-7b/model.json
Normal file
@ -0,0 +1,23 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/janhq/trinity-v1-GGUF/resolve/main/trinity-v1.Q4_K_M.gguf",
|
||||
"id": "trinity-v1-7b",
|
||||
"object": "model",
|
||||
"name": "Trinity 7B Q4",
|
||||
"version": "1.0",
|
||||
"description": "Trinity is an experimental model merge of GreenNodeLM & LeoScorpius using the Slerp method. Recommended for daily assistance purposes.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 2048,
|
||||
"prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
|
||||
},
|
||||
"parameters": {
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "Jan",
|
||||
"tags": ["7B", "Merged", "Featured"],
|
||||
"size": 4370000000,
|
||||
"cover": "https://raw.githubusercontent.com/janhq/jan/main/models/trinity-v1-7b/cover.png"
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
@ -1,23 +0,0 @@
|
||||
{
|
||||
"source_url": "https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/resolve/main/zephyr-7b-beta.Q4_K_M.gguf",
|
||||
"id": "zephyr-beta-7b",
|
||||
"object": "model",
|
||||
"name": "Zephyr Beta 7B Q4",
|
||||
"version": "1.0",
|
||||
"description": "The Zephyr-7B-β model is trained by HuggingFace, designed to function as a practical assistant. It has been fine-tuned from the mistralai/Mistral-7B-v0.1 base model, utilizing a combination of public and synthetic datasets with the application of Direct Preference Optimization.",
|
||||
"format": "gguf",
|
||||
"settings": {
|
||||
"ctx_len": 2048,
|
||||
"prompt_template": "<|system|>\n{system_message}</s>\n<|user|>\n{prompt}</s>\n<|assistant|>"
|
||||
},
|
||||
"parameters": {
|
||||
"max_tokens": 2048
|
||||
},
|
||||
"metadata": {
|
||||
"author": "HuggingFaceH4, The Bloke",
|
||||
"tags": ["7B", "Finetuned"],
|
||||
"size": 4370000000
|
||||
},
|
||||
"engine": "nitro"
|
||||
}
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user