codellama
codellama copied to clipboard
meta-llama
Inference code for CodeLlama models
The new CodeLlama70b Instruct model seem to have incorrect settings for `rope_theta` and `max_position_embeddings`. CodeLlama 34b Values: ``` "rope_theta": 1000000 "max_position_embeddings": 16384 ``` CodeLlama 70b Values: ``` "rope_theta": 10000 "max_position_embeddings":...
I am getting a checksum failures for 70B Instruct and Python: CodeLlama-70b-Instruct: Checking checksums Warning: Hash size is wrong, maybe you want to use 'sha1sum' or 'ripemd160sum' consolidated.00.pth: FAILED consolidated.01.pth:...
Summary: The current script for downloading models, while supposedly secure, leaves much to be desired in terms of user experience. It's a classic case of over-engineering, where the effort to...
**I am using wsl 2 with ubuntu-22.04, this is the gpu information**  **when i run "sudo lshw -C display"**  **I install torch using this command** pip install torch==1.12.1+cu113...
I have difficulty finding docs for the `llama` API. Like, where is the meaning of the parameters defined (some like temperature and top_p I can guess but others...), how is...
Hello, I am trying to reproduce the infilling results on HumanEval (Table 14 CodeLLAMA 7B SPM, pass@1=83%). I am using the single-line benchmark from https://github.com/openai/human-eval-infilling. I use the below code...
We are aware that the knowledge cutoff date for Llama-2 series models are Sep 2022 according to their model card. What's the knowledge cutoff date for CodeLlama? Neither the model...
Hi, Did the instructions from the readme.md. Got the url in the email, ran download.sh, entered "CodeLlama-7b-Python" in the models to download; then I get this error: Why? Thank you....
