610a384af8
* add: qwen 7B * add: gemma 7B * add: qwen prompt tempalte * fix: prompt template gemma 7b * add: gemma 2b * fix: correct id gemma 2b * chore: fix noromaid model size
35 lines
851 B
JSON
35 lines
851 B
JSON
{
|
|
"sources": [
|
|
{
|
|
"filename": "gemma-7b-it-q4_K_M.gguf",
|
|
"url": "https://huggingface.co/mmnga/gemma-7b-it-gguf/resolve/main/gemma-7b-it-q4_K_M.gguf"
|
|
}
|
|
],
|
|
"id": "gemma-7b",
|
|
"object": "model",
|
|
"name": "Gemma 7B Q4",
|
|
"version": "1.0",
|
|
"description": "Gemma is built from the same technology with Google's Gemini.",
|
|
"format": "gguf",
|
|
"settings": {
|
|
"ctx_len": 4096,
|
|
"prompt_template": "<start_of_turn>user\n{prompt}<end_of_turn>\n<start_of_turn>model",
|
|
"llama_model_path": "gemma-7b-it-q4_K_M.gguf"
|
|
},
|
|
"parameters": {
|
|
"temperature": 0.7,
|
|
"top_p": 0.95,
|
|
"stream": true,
|
|
"max_tokens": 4096,
|
|
"stop": [],
|
|
"frequency_penalty": 0,
|
|
"presence_penalty": 0
|
|
},
|
|
"metadata": {
|
|
"author": "Google",
|
|
"tags": ["7B", "Finetuned"],
|
|
"size": 5330000000
|
|
},
|
|
"engine": "nitro"
|
|
}
|