36 lines
913 B
JSON
36 lines
913 B
JSON
{
|
|
"sources": [
|
|
{
|
|
"filename": "llama-2-7b-chat.Q4_K_M.gguf",
|
|
"url": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q4_K_M.gguf"
|
|
}
|
|
],
|
|
"id": "llama2-chat-7b",
|
|
"object": "model",
|
|
"name": "Llama 2 Chat 7B Q4",
|
|
"version": "1.0",
|
|
"description": "Llama 2 specifically designed for a comprehensive understanding the world.",
|
|
"format": "gguf",
|
|
"settings": {
|
|
"ctx_len": 4096,
|
|
"prompt_template": "[INST] <<SYS>>\n{system_message}<</SYS>>\n{prompt}[/INST]",
|
|
"llama_model_path": "llama-2-7b-chat.Q4_K_M.gguf",
|
|
"ngl": 33
|
|
},
|
|
"parameters": {
|
|
"temperature": 0.7,
|
|
"top_p": 0.95,
|
|
"stream": true,
|
|
"max_tokens": 4096,
|
|
"stop": [],
|
|
"frequency_penalty": 0,
|
|
"presence_penalty": 0
|
|
},
|
|
"metadata": {
|
|
"author": "MetaAI",
|
|
"tags": ["7B", "Foundational Model"],
|
|
"size": 4080000000
|
|
},
|
|
"engine": "nitro"
|
|
}
|