Not-For-All-Audiences

Instructions to use TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6 with Transformers:

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

pipe = pipeline("text-generation", model="TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6")
model = AutoModelForMultimodalLM.from_pretrained("TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6

SGLang

How to use TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6 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 "TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6" \
    --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": "TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6",
		"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 "TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6" \
        --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": "TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6 with Docker Model Runner:
```
docker model run hf.co/TeeZee/Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6
```

Xwin-LM-70B-V0.1_Limarpv3-bpw2.4-h6 / output-00002-of-00003.safetensors

TeeZee

Upload output-00002-of-00003.safetensors with huggingface_hub

2193ef0 verified over 2 years ago

download

history blame contribute delete

8.52 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 9511e1bb52b2178bd69d77eca4ed5e468cf9f453e5534e74e7a3677364aa6a30
Size of remote file:: 8.52 GB
SHA256:: 2c72238a954edac67b0e68552b95dd6f49f867397a29686d0696abec6353fe7b

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.