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

Libraries

How to use rishanthrajendhran/VeriFastScore with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rishanthrajendhran/VeriFastScore")
model = AutoModelForCausalLM.from_pretrained("rishanthrajendhran/VeriFastScore")
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 rishanthrajendhran/VeriFastScore with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/rishanthrajendhran/VeriFastScore

SGLang

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

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

rishanthrajendhran commited on Jun 11, 2025

Commit

6ba7858

verified ·

1 Parent(s): 193296f

Corrected typos in README

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -109,7 +109,7 @@ conversation_history = [
     "content": prompt
   }
 ]
-inputs = self.tokenizer.apply_chat_template(
     conversation=conversation_history,
     add_generation_prompt=True,
     tokenize=True,
@@ -118,7 +118,7 @@ inputs = self.tokenizer.apply_chat_template(
 ).to(model.device)
 outputs = model.generate(**inputs, max_new_tokens=2048)
-print(tokenizer.decode(outputs, skip_special_tokens=True))
 ```
 ## Training Details
@@ -145,7 +145,7 @@ In the original VeriFastScore pipeline, evidence is aggregated at the sentence l
 - **Training regime:** : bf16 mixed precision
 - **Optimizer**: AdamW
-- **Scheduler**: Cosine decay (optional placeholder)
 - **Batch size**: 8 (effective)
 - **Epochs**: 10 (5+5)

     "content": prompt
   }
 ]
+inputs = tokenizer.apply_chat_template(
     conversation=conversation_history,
     add_generation_prompt=True,
     tokenize=True,
 ).to(model.device)
 outputs = model.generate(**inputs, max_new_tokens=2048)
+print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
 ```
 ## Training Details
 - **Training regime:** : bf16 mixed precision
 - **Optimizer**: AdamW
+- **Scheduler**: Cosine decay
 - **Batch size**: 8 (effective)
 - **Epochs**: 10 (5+5)