Instructions to use codellama/CodeLlama-13b-Instruct-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codellama/CodeLlama-13b-Instruct-hf with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="codellama/CodeLlama-13b-Instruct-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codellama/CodeLlama-13b-Instruct-hf")
model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-13b-Instruct-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codellama/CodeLlama-13b-Instruct-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codellama/CodeLlama-13b-Instruct-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codellama/CodeLlama-13b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/codellama/CodeLlama-13b-Instruct-hf

SGLang

How to use codellama/CodeLlama-13b-Instruct-hf with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "codellama/CodeLlama-13b-Instruct-hf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codellama/CodeLlama-13b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "codellama/CodeLlama-13b-Instruct-hf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codellama/CodeLlama-13b-Instruct-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use codellama/CodeLlama-13b-Instruct-hf with Docker Model Runner:
```
docker model run hf.co/codellama/CodeLlama-13b-Instruct-hf
```

huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name'

#13

by hwz05 - opened Feb 23, 2024

Discussion

hwz05

Feb 23, 2024

when i use snapshot_down to download model codellama/CodeLlama-13b-Instruct-hf to local path "/data/home/zanehu/hwz_local/DB-GPT-Hub/dbgpt_hub/ft_local/codellama/CodeLlama-12b-Instruct-hf" ,then update file args in model_name_or_path of "dbgpt_hub/scripts/train_sft.sh" model_name_or_path="/data/home/zanehu/hwz_local/DB-GPT-Hub/dbgpt_hub/ft_local/codellama/CodeLlama-12b-Instruct-hf",but i still appear error below:
W&B offline. Running your script from this directory will only write metadata locally. Use wandb disabled to completely turn off W&B.
/data/home/zanehu/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/transformers/deepspeed.py:23: FutureWarning: transformers.deepspeed module is deprecated and will be removed in a future version. Please import deepspeed modules directly from transformers.integrations
warnings.warn(
[INFO|training_args.py:1345] 2024-02-23 11:10:27,627 >> Found safetensors installation, but --save_safetensors=False. Safetensors should be a preferred weights saving format due to security and performance reasons. If your model cannot be saved by safetensors please feel free to open an issue at https://github.com/huggingface/safetensors!
[INFO|training_args.py:1798] 2024-02-23 11:10:27,628 >> PyTorch: setting up devices
/data/home/zanehu/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/transformers/training_args.py:1711: FutureWarning: --push_to_hub_token is deprecated and will be removed in version 5 of 🤗 Transformers. Use --hub_token instead.
warnings.warn(
/data/home/zanehu/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/datasets/load.py:2089: FutureWarning: 'use_auth_token' was deprecated in favor of 'token' in version 2.14.0 and will be removed in 3.0.0.
You can remove this warning by passing 'token=None' instead.
warnings.warn(
Using custom data configuration default-e3c6bc7f485aed74
Loading Dataset Infos from /data/home/zanehu/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/datasets/packaged_modules/json
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /data/home/zanehu/.cache/huggingface/datasets/json/default-e3c6bc7f485aed74/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96
Found cached dataset json (/data/home/zanehu/.cache/huggingface/datasets/json/default-e3c6bc7f485aed74/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96)
Loading Dataset info from /data/home/zanehu/.cache/huggingface/datasets/json/default-e3c6bc7f485aed74/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96
Traceback (most recent call last):
File "/data/home/zanehu/hwz_local/DB-GPT-Hub/dbgpt_hub/train/sft_train.py", line 172, in
train()
File "/data/home/zanehu/hwz_local/DB-GPT-Hub/dbgpt_hub/train/sft_train.py", line 149, in train
run_sft(
File "/data/home/zanehu/hwz_local/DB-GPT-Hub/dbgpt_hub/train/sft_train.py", line 48, in run_sft
model, tokenizer = load_model_and_tokenizer(
File "/data/home/zanehu/hwz_local/DB-GPT-Hub/dbgpt_hub/llm_base/load_tokenizer.py", line 175, in load_model_and_tokenizer
tokenizer = AutoTokenizer.from_pretrained(
File "/data/home/zanehu/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 701, in from_pretrained
tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs)
File "/data/home/zanehu/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 534, in get_tokenizer_config
resolved_config_file = cached_file(
File "/data/home/zanehu/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/transformers/utils/hub.py", line 429, in cached_file
resolved_file = hf_hub_download(
File "/data/home/zanehu/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 110, in _inner_fn
validate_repo_id(arg_value)
File "/data/home/zanehu/anaconda3/envs/dbgpt_hub/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 158, in validate_repo_id
raise HFValidationError(
huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/data/home/zanehu/hwz_local/DB-GPT-Hub/dbgpt_hub/ft_local/codellama/CodeLlama-12b-Instruct-hf'. Use repo_type argument if needed.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment