Skip to content

Commit

Permalink
Code Llama
Browse files Browse the repository at this point in the history
  • Loading branch information
KillianLucas committed Aug 28, 2023
1 parent ecba9ef commit 0dcf5e4
Showing 1 changed file with 2 additions and 0 deletions.
2 changes: 2 additions & 0 deletions interpreter/llama_2.py
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,8 @@ def get_llama_2_instance():
code_llama_13b = [
{'URL': 'https://huggingface.co/TheBloke/CodeLlama-13B-oasst-sft-v10-GGUF/resolve/main/codellama-13b-oasst-sft-v10.Q4_K_M.gguf', 'Param': '13B', 'Bits': 8, 'Size': '13.83 GB', 'RAM': '16.33 GB', 'Description': 'Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.'}
]

print("Testing")

#all_models = llama_2_7b + llama_2_13b + code_llama_13b
all_models = code_llama_13b
Expand Down

0 comments on commit 0dcf5e4

Please sign in to comment.