Instructions to use TheBloke/Code-290k-13B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheBloke/Code-290k-13B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TheBloke/Code-290k-13B-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheBloke/Code-290k-13B-AWQ")
model = AutoModelForCausalLM.from_pretrained("TheBloke/Code-290k-13B-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TheBloke/Code-290k-13B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheBloke/Code-290k-13B-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/Code-290k-13B-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheBloke/Code-290k-13B-AWQ

SGLang

How to use TheBloke/Code-290k-13B-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/Code-290k-13B-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/Code-290k-13B-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/Code-290k-13B-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/Code-290k-13B-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheBloke/Code-290k-13B-AWQ with Docker Model Runner:
```
docker model run hf.co/TheBloke/Code-290k-13B-AWQ
```

Noobs's question

by kekawia - opened Feb 17, 2024

Discussion

kekawia

Feb 17, 2024

can i run this ?
-- RTX 3060 12go vram / 32 ram --

kekawia changed discussion status to closed Feb 17, 2024

kekawia changed discussion status to open Feb 17, 2024

YaTharThShaRma999

Feb 18, 2024

@kekawia
yeah you can 100% run this but probably not at 290k context. Awq relies mostly on vram so not a lot of context(maybe 8k?) Gguf quants with llama.cpp should help you run much more context since it can utilize cpu and it might reach like 60k context? definitely much more then 8k however

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