Instructions to use principled-intelligence/claim-extraction with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use principled-intelligence/claim-extraction with Transformers:

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

pipe = pipeline("text-generation", model="principled-intelligence/claim-extraction")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("principled-intelligence/claim-extraction")
model = AutoModelForCausalLM.from_pretrained("principled-intelligence/claim-extraction")
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

vLLM

How to use principled-intelligence/claim-extraction with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/principled-intelligence/claim-extraction

SGLang

How to use principled-intelligence/claim-extraction 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 "principled-intelligence/claim-extraction" \
    --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": "principled-intelligence/claim-extraction",
		"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 "principled-intelligence/claim-extraction" \
        --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": "principled-intelligence/claim-extraction",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use principled-intelligence/claim-extraction with Docker Model Runner:
```
docker model run hf.co/principled-intelligence/claim-extraction
```

edobobo commited on 15 days ago

Commit

6a79360

verified ·

1 Parent(s): d420a64

Upload ClaimExtractionPipeline

Browse files

Files changed (1) hide show

claim_extractor.py +1 -7

claim_extractor.py CHANGED Viewed

@@ -20,10 +20,8 @@ class ClaimExtractionPipeline(Pipeline):
         tokenizer=None,
         skip_evidences: bool = True,
         max_new_tokens: int = 20_000,
-        do_sample: bool = False,
         temperature: float = 0.7,
-        frequency_penalty: float = 0.0,
-        presence_penalty: float = 1.5,
         repetition_penalty: float = 1.0,
         top_p: float = 0.8,
         top_k: int = 20,
@@ -51,8 +49,6 @@ class ClaimExtractionPipeline(Pipeline):
         self.max_new_tokens = max_new_tokens
         self.do_sample = do_sample
         self.temperature = temperature
-        self.frequency_penalty = frequency_penalty
-        self.presence_penalty = presence_penalty
         self.repetition_penalty = repetition_penalty
         self.top_p = top_p
         self.top_k = top_k
@@ -113,8 +109,6 @@ class ClaimExtractionPipeline(Pipeline):
                 max_new_tokens=self.max_new_tokens,
                 do_sample=self.do_sample,
                 temperature=self.temperature,
-                frequency_penalty=self.frequency_penalty,
-                presence_penalty=self.presence_penalty,
                 repetition_penalty=self.repetition_penalty,
                 top_p=self.top_p,
                 top_k=self.top_k,

         tokenizer=None,
         skip_evidences: bool = True,
         max_new_tokens: int = 20_000,
+        do_sample: bool = True,
         temperature: float = 0.7,
         repetition_penalty: float = 1.0,
         top_p: float = 0.8,
         top_k: int = 20,
         self.max_new_tokens = max_new_tokens
         self.do_sample = do_sample
         self.temperature = temperature
         self.repetition_penalty = repetition_penalty
         self.top_p = top_p
         self.top_k = top_k
                 max_new_tokens=self.max_new_tokens,
                 do_sample=self.do_sample,
                 temperature=self.temperature,
                 repetition_penalty=self.repetition_penalty,
                 top_p=self.top_p,
                 top_k=self.top_k,