Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

chore: add model.json for Llama3 and other outdated model version #2773

Merged
merged 8 commits into from
Apr 22, 2024
Prev Previous commit
Next Next commit
Update extensions/inference-nitro-extension/resources/models/llama3-8…
…b-instruct/model.json
  • Loading branch information
louis-jan committed Apr 22, 2024
commit aefc859a166249c4e9c2ec4ce898da33e4568f73
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 12,7 @@
"description": "The latest model from MetaAI",
Van-QA marked this conversation as resolved.
Show resolved Hide resolved
"format": "gguf",
"settings": {
"ctx_len": 4096,
"ctx_len": 8192,
"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",
hahuyhoang411 marked this conversation as resolved.
Show resolved Hide resolved
"llama_model_path": "Meta-Llama-3-8B-Instruct-Q4_K_M.gguf"
},
Expand Down
Loading