Instructions to use skrishna/sft-ref-policy-copy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use skrishna/sft-ref-policy-copy with Transformers:

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

pipe = pipeline("text-generation", model="skrishna/sft-ref-policy-copy")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("skrishna/sft-ref-policy-copy")
model = AutoModelForCausalLM.from_pretrained("skrishna/sft-ref-policy-copy", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use skrishna/sft-ref-policy-copy with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/skrishna/sft-ref-policy-copy

SGLang

How to use skrishna/sft-ref-policy-copy 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 "skrishna/sft-ref-policy-copy" \
    --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": "skrishna/sft-ref-policy-copy",
		"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 "skrishna/sft-ref-policy-copy" \
        --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": "skrishna/sft-ref-policy-copy",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use skrishna/sft-ref-policy-copy with Docker Model Runner:
```
docker model run hf.co/skrishna/sft-ref-policy-copy
```

sft-ref-policy-copy / model.safetensors

skrishna

Upload LlamaForCausalLM

46a4cd7 verified about 1 year ago

Download

History Blame

538 MB

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:: a887c72c8ddcbdaee15c6c9dc4da911b5f3cd3813e0f6cfc25d087ec0d300a82
Size of remote file:: 538 MB
SHA256:: 877c1e76d986761f3be988d82b922ecfe3bfa4a7c59c1d96006a2c1af8bdadc4

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