Instructions to use TheBloke/CodeLlama-13B-Python-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/CodeLlama-13B-Python-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/CodeLlama-13B-Python-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/CodeLlama-13B-Python-AWQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/CodeLlama-13B-Python-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/CodeLlama-13B-Python-AWQ 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-AWQ"
# 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-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/CodeLlama-13B-Python-AWQ

SGLang

How to use TheBloke/CodeLlama-13B-Python-AWQ 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-AWQ" \
    --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-AWQ",
		"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-AWQ" \
        --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-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/CodeLlama-13B-Python-AWQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/CodeLlama-13B-Python-AWQ
```

TheBloke commited on Sep 27, 2023

Commit

702cebe

1 Parent(s): 68acbe3

Update base_model formatting

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -1,11 +1,13 @@
 ---
-base_model: https://huggingface.co/codellama/CodeLlama-13b-python-hf
-inference: false
 language:
 - code
 license: llama2
-model_creator: Meta
 model_name: CodeLlama 13B Python
 model_type: llama
 pipeline_tag: text-generation
 prompt_template: '[INST] Write code to solve the following coding problem that obeys
@@ -18,8 +20,6 @@ prompt_template: '[INST] Write code to solve the following coding problem that o
   '
 quantized_by: TheBloke
-tags:
-- llama-2
 ---
 <!-- header start -->

 ---
 language:
 - code
 license: llama2
+tags:
+- llama-2
 model_name: CodeLlama 13B Python
+base_model: codellama/CodeLlama-13b-python-hf
+inference: false
+model_creator: Meta
 model_type: llama
 pipeline_tag: text-generation
 prompt_template: '[INST] Write code to solve the following coding problem that obeys
   '
 quantized_by: TheBloke
 ---
 <!-- header start -->