1c5b6355d9
* chore: add llama 3.1 8B gguf model * chore: add llama3.1 70B model * chore: add models to rollup * chore: fix tag * chore: fix size * fix: 8b model * Chore/add gemma2 model (#3471) * feat: add gemma 2 * feat: add gemma 2 * feat: correct ngl --------- Co-authored-by: Van QA <van@jan.ai> * feat: add featured tag --------- Co-authored-by: Van Pham <64197333+Van-QA@users.noreply.github.com> Co-authored-by: Van QA <van@jan.ai>
44 lines
1.0 KiB
JSON
44 lines
1.0 KiB
JSON
{
|
|
"sources": [
|
|
{
|
|
"filename": "gemma-2-2b-it-Q4_K_M.gguf",
|
|
"url": "https://huggingface.co/bartowski/gemma-2-2b-it-GGUF/resolve/main/gemma-2-2b-it-Q4_K_M.gguf"
|
|
}
|
|
],
|
|
"id": "gemma-2-2b-it",
|
|
"object": "model",
|
|
"name": "Gemma 2 2B Q4",
|
|
"version": "1.0",
|
|
"description": "Gemma is built from the same technology with Google's Gemini.",
|
|
"format": "gguf",
|
|
"settings": {
|
|
"ctx_len": 8192,
|
|
"prompt_template": "<bos><start_of_turn>user\n{prompt}<end_of_turn>\n<start_of_turn>model\n<end_of_turn>\n<start_of_turn>model\n",
|
|
"llama_model_path": "gemma-2-2b-it-Q4_K_M.gguf",
|
|
"ngl": 27
|
|
},
|
|
"parameters": {
|
|
"temperature": 0.7,
|
|
"top_p": 0.95,
|
|
"stream": true,
|
|
"max_tokens": 8192,
|
|
"stop": [
|
|
"<end_of_turn>"
|
|
],
|
|
"frequency_penalty": 0,
|
|
"presence_penalty": 0
|
|
},
|
|
"metadata": {
|
|
"author": "Google",
|
|
"tags": [
|
|
"2B",
|
|
"Tiny",
|
|
"Conversational",
|
|
"Text-generation",
|
|
"Featured"
|
|
],
|
|
"size": 1710000000
|
|
},
|
|
"engine": "nitro"
|
|
}
|