0dd12950df
fix(capybara): change description + parameters fix(codeninja): update description + add parameters delete(magicoder): this model is failed to load due to gguf fix(deepseek-1.3b): update description + add parameters fix(deepseek-34b): update description + add parameters fix(dolphin8x7b): update description + parameters fix(llama2-chat-7b): update description + add parameters fix(llama2-chat-70b): update description + add parameters fix(mistral-7b): update description + add parameters fix(mistral): degrade to v0.1 due to giberish output from v0.2 fix(mixtral): update desciption + parameters fix(noromaid): update description + parameters fix(mistral7b): correct the prompt template update(openchat): add parameters fix(openhermesneural): update parameter + description fix(openhermesneural): update max_tokens delete(pandora): remove pandora fix(phi2): update parameter update(phind34b): update description + change to q4 + add parameter update(solar-slerp): update parameter fix(starling): update description + parameter fix(openchat): add to recommended fix(stealth): add parameters fix(tinyllama): update description + parameters fix(trinity): update description + parameters fix(tulu2): update description + parameters fix(stealth): change max_tokens to 4096 update(wizardcoder): update parameter + description update(wizardcoder): update description update(wizardcoder): change to q4 fix(yarn-mistral): update parameters fix(yarn-mistral): change to q4 update(wizardcoder): correct the size of q4 model fix(model-extension): pump to 1.0.20 fix(tinyllama): change to q8 fix(phi-2): change to q8 fix(deepseek34b): change to q4 fix(mistral7b): update the stop token fix(starling): remove recommended
27 lines
800 B
JSON
27 lines
800 B
JSON
{
|
|
"source_url": "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf",
|
|
"id": "tinyllama-1.1b",
|
|
"object": "model",
|
|
"name": "TinyLlama Chat 1.1B Q4",
|
|
"version": "1.0",
|
|
"description": "TinyLlama is a tiny model with only 1.1B. It's a good model for less powerful computers.",
|
|
"format": "gguf",
|
|
"settings": {
|
|
"ctx_len": 2048,
|
|
"prompt_template": "<|system|>\n{system_message}<|user|>\n{prompt}<|assistant|>"
|
|
},
|
|
"parameters": {
|
|
"temperature": 0.7,
|
|
"top_p": 0.95,
|
|
"stream": true,
|
|
"max_tokens": 2048,
|
|
"frequency_penalty": 0,
|
|
"presence_penalty": 0
|
|
},
|
|
"metadata": {
|
|
"author": "TinyLlama",
|
|
"tags": ["Tiny", "Foundation Model"],
|
|
"size": 1170000000
|
|
},
|
|
"engine": "nitro"
|
|
} |