Instructions to use nitin1pawar/slm125m-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nitin1pawar/slm125m-instruct with Transformers:

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

pipe = pipeline("text-generation", model="nitin1pawar/slm125m-instruct")
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("nitin1pawar/slm125m-instruct")
model = AutoModelForCausalLM.from_pretrained("nitin1pawar/slm125m-instruct", 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 nitin1pawar/slm125m-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nitin1pawar/slm125m-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nitin1pawar/slm125m-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nitin1pawar/slm125m-instruct

SGLang

How to use nitin1pawar/slm125m-instruct 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 "nitin1pawar/slm125m-instruct" \
    --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": "nitin1pawar/slm125m-instruct",
		"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 "nitin1pawar/slm125m-instruct" \
        --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": "nitin1pawar/slm125m-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nitin1pawar/slm125m-instruct with Docker Model Runner:
```
docker model run hf.co/nitin1pawar/slm125m-instruct
```

slm125m-instruct

A 126M-parameter legal/financial Q&A model, supervised fine-tuned from nitin1pawar/slm125m-base — a base model that was itself pretrained from scratch (corpus, tokenizer and weights) for $31.76.

Trained in RAFT style: each example pairs a question with retrieved passages, and a quarter of the training set contains passages that do not answer the question, so the model learns to say so instead of inventing an answer.

Prompt format

<|bos|><|system|>{system}<|user|>{user}<|assistant|>{answer}<|eos|>

tokenizer.apply_chat_template is configured, so:

messages = [
    {"role": "system", "content": "You are a legal and financial assistant. ..."},
    {"role": "user", "content": "Passage 1:\n...\n\nQuestion: ..."},
]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)

When the passages do not contain the answer the model replies:

The passage does not provide enough information to answer this question.

Training data

10,000 synthetic Q&A pairs generated with gpt-5-mini from the model's own pretraining corpus (US case law + SEC filings + educational web text), then graded by an LLM judge on groundedness, correctness, answerability and form. Judge pass rate 88.4%. Questions were deduplicated by exact hash and by 5-gram Jaccard overlap.

Passages were drawn from the deduplicated and decontaminated corpus, so CaseHOLD and LexGLUE case_hold remain genuinely held out.

slice	share
closed_book	1,584
instruction	787
negative	2,511
positive	5,118

Training

148 steps over 1 epochs (9.7M tokens, 62s on 1×H100), full-parameter (no LoRA), AdamW, peak LR 8e-05 cosine to 0, bf16. Loss is computed on answer tokens only — question and context tokens are masked out.

Results

metric	value
Val answer-token loss	1.6840 (ppl 5.39)
Refusal recall (no answer in context → refuses)	91.0%
False refusal rate (answer present → wrongly refuses)	15.3%
Base-corpus perplexity after SFT	10.56 (was 8.11 before)

Limitations

125M parameters. It produces fluent but frequently incorrect legal and financial text, its knowledge is bounded by a 2.07B-token corpus, and the training answers were written by another language model rather than by lawyers. Context is capped at 1,024 tokens. Not legal or financial advice.

Downloads last month: 7

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for nitin1pawar/slm125m-instruct

Base model

nitin1pawar/slm125m-base

Finetuned

(1)

this model