42 lines
1.2 KiB
JSON
42 lines
1.2 KiB
JSON
{
|
|
"sources": [
|
|
{
|
|
"filename": "Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf",
|
|
"url": "https://huggingface.co/bartowski/Meta-Llama-3.1-70B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf"
|
|
}
|
|
],
|
|
"id": "llama3.1-70b-instruct",
|
|
"object": "model",
|
|
"name": "Llama 3.1 70B Instruct Q4",
|
|
"version": "1.2",
|
|
"description": "Meta's Llama 3.1 excels at general usage situations, including chat, general world knowledge, and coding.",
|
|
"format": "gguf",
|
|
"settings": {
|
|
"ctx_len": 131072,
|
|
"prompt_template": "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n",
|
|
"llama_model_path": "Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf",
|
|
"ngl": 33
|
|
},
|
|
"parameters": {
|
|
"temperature": 0.7,
|
|
"top_p": 0.95,
|
|
"stream": true,
|
|
"max_tokens": 8192,
|
|
"stop": [
|
|
"<|end_of_text|>",
|
|
"<|eot_id|>",
|
|
"<|eom_id|>"
|
|
],
|
|
"frequency_penalty": 0,
|
|
"presence_penalty": 0
|
|
},
|
|
"metadata": {
|
|
"author": "MetaAI",
|
|
"tags": [
|
|
"70B"
|
|
],
|
|
"size": 42500000000
|
|
},
|
|
"engine": "nitro"
|
|
}
|