Text Generation
Transformers
Safetensors
code
llama
llama-2
custom_code
text-generation-inference
4-bit precision
gptq
Instructions to use TheBloke/CodeLlama-13B-Python-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheBloke/CodeLlama-13B-Python-GPTQ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TheBloke/CodeLlama-13B-Python-GPTQ", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TheBloke/CodeLlama-13B-Python-GPTQ", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("TheBloke/CodeLlama-13B-Python-GPTQ", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use TheBloke/CodeLlama-13B-Python-GPTQ with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TheBloke/CodeLlama-13B-Python-GPTQ" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheBloke/CodeLlama-13B-Python-GPTQ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TheBloke/CodeLlama-13B-Python-GPTQ
- SGLang
How to use TheBloke/CodeLlama-13B-Python-GPTQ 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 "TheBloke/CodeLlama-13B-Python-GPTQ" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheBloke/CodeLlama-13B-Python-GPTQ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "TheBloke/CodeLlama-13B-Python-GPTQ" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheBloke/CodeLlama-13B-Python-GPTQ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TheBloke/CodeLlama-13B-Python-GPTQ with Docker Model Runner:
docker model run hf.co/TheBloke/CodeLlama-13B-Python-GPTQ
Commit History
-
Upload README.md
9dc3c70
-
Upload README.md
8f8f7db
-
Initial GPTQ model commit
448321e -
Initial GPTQ model commit
5c57b4a -
Initial GPTQ model commit
d3c6c12 -
Initial GPTQ model commit
3a17d77 -
Initial GPTQ model commit
08431b6 -
Initial GPTQ model commit
a9377ec -
Initial GPTQ model commit
eca4994 -
Initial GPTQ model commit
0a154ed -
Initial GPTQ model commit
99c45d2 -
Initial GPTQ model commit
12127e8 -
Initial GPTQ model commit
8da773d -
Initial GPTQ model commit
bf563cb
-
Add pad_token_id to config.json
d9dcbd4 -
Fix generation_config.json
cceb62c -
Initial GPTQ model commit
90d9cdf -
Initial GPTQ model commit
a163681 -
Initial GPTQ model commit
30682fe -
Initial GPTQ model commit
8c0d62e -
Initial GPTQ model commit
45ba810 -
Initial GPTQ model commit
bb530de -
Initial GPTQ model commit
db5146a -
Initial GPTQ model commit
7238820 -
Initial GPTQ model commit
127080a -
Initial GPTQ model commit
e22422b -
Initial GPTQ model commit
3fd27de -
Initial GPTQ model commit
170503c -
Initial GPTQ model commit
78c97f2 -
Initial GPTQ model commit
dc62781 -
Initial GPTQ model commit
2ff8e23 -
initial commit
71634f7