codellama

codellama copied to clipboard

What is the max length could the codellama-2-7B generate?

2

I was doing an inference work using codellama-2-7B. Here is my code: ``` inputs_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(self.device) generate_ids=model.generate(inputs_ids,max_new_tokens=1024,num_return_sequences=1,pad_token_id=tokenizer.eos_token_id) output = tokenizer.decode(generate_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=False) ``` I want to know the maximum...

Uestc-Young

ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: -9)

1

## Problem Description After completing setup for CodeLlama, from the [README.md](https://github.com/facebookresearch/codellama), when I attempt to run any of the examples, with the specified commands: ``` torchrun --nproc_per_node 1 example_completion.py --ckpt_dir...

kgopfa

Run code llama from Hugging Face locally with GPU

1

I have trying to host the Code Llama from Hugging Face locally and trying to run it. It runs soley on CPU and it is not utilizing GPU available in...

tabish0

How to add tokens to tokenizer?

1

I want to add some tokens like `[BOST]` to the tokenizer so that it does not split these. How can I achieve this? Any suggestions are welcome. Huggingface provides functions...

abs-xyz

Cannot run HF example codes on all three codeLlama-Python-hf models

1

I understand this might be a huggingface-related problem but I cannot find the answer anywhere so I come to ask for help. On huggingface there is a example code for...

jessyford

instruct model's performance become poor when switching to different format

6

I use 7b and 13b-instruct model to do program analysis task. When I use original format 7b-Instruct and 13b-Instruct model, following `example_chat_completion.py`, everything is all right. But when I use...

for-just-we

Fine-tuning Code Llama on my own code

3

Thank you for this amazing effort! I would like to fine-tune code llama on my own Python code, let's call it MyPackage for now. Ultimately, I would like to ask...

g12bftd

Hi, I'm testing codellama, and I would like a guide on how to enable it to accept the sending of 100K input tokens. From what I understand, this is done...

harlequen

Is download.sh providing the correct tokenizer.model files?

1

When I try to run a model .. ``` torchrun example_js.py \ --ckpt_dir CodeLlama-13b-Instruct \ --tokenizer_path CodeLlama-13b-Instruct/tokenizer.model \ --max_seq_len 1024 --max_batch_size 4 --nproc_per_node 2 ``` example_js is the same as...

dveb8886

Unable to Download Code-Llama 7B via the download.sh Script

8

Hello! I signed up to download the Code-Llama model from Meta. I received the email with the Unique Custom URL. **However, when I attempt to download the model, the script...

joseeliaschavez