Instructions to use selfrag/selfrag_llama2_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use selfrag/selfrag_llama2_7b with Transformers:

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

pipe = pipeline("text-generation", model="selfrag/selfrag_llama2_7b")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("selfrag/selfrag_llama2_7b")
model = AutoModelForCausalLM.from_pretrained("selfrag/selfrag_llama2_7b", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use selfrag/selfrag_llama2_7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "selfrag/selfrag_llama2_7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "selfrag/selfrag_llama2_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/selfrag/selfrag_llama2_7b

SGLang

How to use selfrag/selfrag_llama2_7b 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 "selfrag/selfrag_llama2_7b" \
    --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": "selfrag/selfrag_llama2_7b",
		"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 "selfrag/selfrag_llama2_7b" \
        --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": "selfrag/selfrag_llama2_7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use selfrag/selfrag_llama2_7b with Docker Model Runner:
```
docker model run hf.co/selfrag/selfrag_llama2_7b
```

selfrag_llama2_7b / special_tokens_map.json

yizhongw

Checkpoint first release.

7f25cee about 3 years ago

Raw History Blame Contribute Delete

470 Bytes

{
  "additional_special_tokens": [
    "[No Retrieval]",
    "[Retrieval]",
    "[Continue to Use Evidence]",
    "[Irrelevant]",
    "[Relevant]",
    "<paragraph>",
    "</paragraph>",
    "[Utility:1]",
    "[Utility:2]",
    "[Utility:3]",
    "[Utility:4]",
    "[Utility:5]",
    "[Fully supported]",
    "[Partially supported]",
    "[No support / Contradictory]"
  ],
  "bos_token": "<s>",
  "eos_token": "</s>",
  "pad_token": "<pad>",
  "unk_token": "<unk>"
}

	{
	"additional_special_tokens": [
	"[No Retrieval]",
	"[Retrieval]",
	"[Continue to Use Evidence]",
	"[Irrelevant]",
	"[Relevant]",
	"<paragraph>",
	"</paragraph>",
	"[Utility:1]",
	"[Utility:2]",
	"[Utility:3]",
	"[Utility:4]",
	"[Utility:5]",
	"[Fully supported]",
	"[Partially supported]",
	"[No support / Contradictory]"
	],
	"bos_token": "<s>",
	"eos_token": "</s>",
	"pad_token": "<pad>",
	"unk_token": "<unk>"
	}