Instructions to use AdarshSingh7647/Std-SFT-Passage-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AdarshSingh7647/Std-SFT-Passage-0.6B with Transformers:

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

pipe = pipeline("text-generation", model="AdarshSingh7647/Std-SFT-Passage-0.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("AdarshSingh7647/Std-SFT-Passage-0.6B")
model = AutoModelForCausalLM.from_pretrained("AdarshSingh7647/Std-SFT-Passage-0.6B", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AdarshSingh7647/Std-SFT-Passage-0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AdarshSingh7647/Std-SFT-Passage-0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AdarshSingh7647/Std-SFT-Passage-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AdarshSingh7647/Std-SFT-Passage-0.6B

SGLang

How to use AdarshSingh7647/Std-SFT-Passage-0.6B 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 "AdarshSingh7647/Std-SFT-Passage-0.6B" \
    --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": "AdarshSingh7647/Std-SFT-Passage-0.6B",
		"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 "AdarshSingh7647/Std-SFT-Passage-0.6B" \
        --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": "AdarshSingh7647/Std-SFT-Passage-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AdarshSingh7647/Std-SFT-Passage-0.6B with Docker Model Runner:
```
docker model run hf.co/AdarshSingh7647/Std-SFT-Passage-0.6B
```

Std-SFT-Passage-0.6B

Qwen3-0.6B passage reranker trained with Std-SFT: the loss is on the teacher's reasoning and the final answer. Code · Eklav version

Results

BRIGHT nDCG@10	Qwen3-4B	Qwen3-8B	GLM-Z1-9B	Qwen3-14B
Std-SFT	29.3	31.5	30.1	32.5
Eklav	31.5	34.2	33.2	34.7

Usage

Pointwise reranker in the style of Rank1: the model writes its reasoning, ending in </think> true or </think> false, and relevance is the probability of true at that last token.

from vllm import LLM, SamplingParams
import math

model_id = "AdarshSingh7647/Std-SFT-Passage-0.6B"
model = LLM(model=model_id, max_model_len=16000)
tokenizer = model.get_tokenizer()

def create_prompt(query: str, passage: str) -> str:
    return (
        "Determine if the following passage is relevant to the query. "
        "Answer only with 'true' or 'false'.\n"
        f"Query: {query}\n"
        f"Passage: {passage}\n<think>"
    )

sampling_params = SamplingParams(
    temperature=0,
    max_tokens=8192,
    logprobs=20,
    stop=["</think> true", "</think> false"],
)

def score(query: str, passage: str) -> float:
    prompt = create_prompt(query, passage)
    output = model.generate([prompt], sampling_params)[0].outputs[0]
    # the answer token is usually the second to last logprob step (vLLM's stop
    # string match can consume one extra token, e.g. <|im_end|>, after it), but
    # scan from the end so this is robust to that off by one
    for step in reversed(output.logprobs or []):
        true_lp = next((v.logprob for k, v in step.items() if tokenizer.decode([k]).strip().lower() == "true"), None)
        false_lp = next((v.logprob for k, v in step.items() if tokenizer.decode([k]).strip().lower() == "false"), None)
        if true_lp is not None and false_lp is not None:
            true_score, false_score = math.exp(true_lp), math.exp(false_lp)
            return true_score / (true_score + false_score)
    return 0.5

query = "What causes seasons on Earth?"
passages = [
    "Seasons are caused by the tilt of Earth's axis relative to its orbit around the Sun.",
    "The Great Wall of China is visible from space, according to popular belief.",
]
ranked = sorted(passages, key=lambda p: score(query, p), reverse=True)
for p in ranked:
    print(p)