Instructions to use meng-lab/NaturalQuestions-InstructRAG-FT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meng-lab/NaturalQuestions-InstructRAG-FT with Transformers:

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

pipe = pipeline("text-generation", model="meng-lab/NaturalQuestions-InstructRAG-FT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meng-lab/NaturalQuestions-InstructRAG-FT")
model = AutoModelForCausalLM.from_pretrained("meng-lab/NaturalQuestions-InstructRAG-FT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meng-lab/NaturalQuestions-InstructRAG-FT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meng-lab/NaturalQuestions-InstructRAG-FT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meng-lab/NaturalQuestions-InstructRAG-FT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meng-lab/NaturalQuestions-InstructRAG-FT

SGLang

How to use meng-lab/NaturalQuestions-InstructRAG-FT 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 "meng-lab/NaturalQuestions-InstructRAG-FT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meng-lab/NaturalQuestions-InstructRAG-FT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "meng-lab/NaturalQuestions-InstructRAG-FT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meng-lab/NaturalQuestions-InstructRAG-FT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meng-lab/NaturalQuestions-InstructRAG-FT with Docker Model Runner:
```
docker model run hf.co/meng-lab/NaturalQuestions-InstructRAG-FT
```

AnonyResearcher commited on Jun 24, 2024

Commit

818ac6a

1 Parent(s): 9bda044

update

Browse files

Files changed (4) hide show

config.json +1 -1
runs/May21_01-05-40_della-k16g2/events.out.tfevents.1716268294.della-k16g2.3064593.0 +0 -3
trainer_state.json +0 -0
training_args.bin +0 -3

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/scratch/gpfs/DANQIC/ym0081/hf_cache/Meta-Llama-3-8B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],

 {
+  "_name_or_path": "meng-lab/NaturalQuestions-InstructRAG-FT",
   "architectures": [
     "LlamaForCausalLM"
   ],

runs/May21_01-05-40_della-k16g2/events.out.tfevents.1716268294.della-k16g2.3064593.0 DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e89becf3a28d8f4c1eee357c5bcc57fa2d6637101164de3d41580957fc833c06
-size 556147

trainer_state.json DELETED Viewed

The diff for this file is too large to render. See raw diff

training_args.bin DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:eab8330d179c77ebbb79ca5eb1e7eeb4fb757adceaf42dfd43f5a67086efe476
-size 5816