Instructions to use chargoddard/llama33b-s2a4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chargoddard/llama33b-s2a4 with Transformers:

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

pipe = pipeline("text-generation", model="chargoddard/llama33b-s2a4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chargoddard/llama33b-s2a4")
model = AutoModelForCausalLM.from_pretrained("chargoddard/llama33b-s2a4")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use chargoddard/llama33b-s2a4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chargoddard/llama33b-s2a4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chargoddard/llama33b-s2a4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/chargoddard/llama33b-s2a4

SGLang

How to use chargoddard/llama33b-s2a4 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 "chargoddard/llama33b-s2a4" \
    --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": "chargoddard/llama33b-s2a4",
		"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 "chargoddard/llama33b-s2a4" \
        --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": "chargoddard/llama33b-s2a4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use chargoddard/llama33b-s2a4 with Docker Model Runner:
```
docker model run hf.co/chargoddard/llama33b-s2a4
```

LLaMA 33b finetuned on wikitext_document_level with combined linear and NTK-aware ROPE scaling (alpha=4, scale=2.) This model will be coherent up to at least 8k context length, but might work beyond that. This is a merged version of llama33b-s2a4-qlora.

Note that this is not an instruct model - this is base LLaMA with an extended sequence length.

Downloads last month: 6

chargoddard
/

llama33b-s2a4

Dataset used to train chargoddard/llama33b-s2a4