Instructions to use sumitguha13/slm125MLIVE-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sumitguha13/slm125MLIVE-sft with Transformers:

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

pipe = pipeline("text-generation", model="sumitguha13/slm125MLIVE-sft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sumitguha13/slm125MLIVE-sft")
model = AutoModelForCausalLM.from_pretrained("sumitguha13/slm125MLIVE-sft")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sumitguha13/slm125MLIVE-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sumitguha13/slm125MLIVE-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sumitguha13/slm125MLIVE-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sumitguha13/slm125MLIVE-sft

SGLang

How to use sumitguha13/slm125MLIVE-sft 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 "sumitguha13/slm125MLIVE-sft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sumitguha13/slm125MLIVE-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "sumitguha13/slm125MLIVE-sft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sumitguha13/slm125MLIVE-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sumitguha13/slm125MLIVE-sft with Docker Model Runner:
```
docker model run hf.co/sumitguha13/slm125MLIVE-sft
```

slm125MLIVE-sft

Instruction fine-tuned (SFT) version of thesreedath/slm-125m-base (125M, LLaMA). Trained on ~8,000 grounded Q&A pairs (RAFT-style: answer from the provided context) synthesized with Gemini 2.5 Flash and grounding-judged.

SFT val perplexity: ~2.71
Format: chat with <|system|> <|user|> <|assistant|> special tokens.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("sumitguha13/slm125MLIVE-sft")
model = AutoModelForCausalLM.from_pretrained("sumitguha13/slm125MLIVE-sft")
prompt = ("<|bos|><|system|>\nYou are a helpful assistant. Answer using only the "
          "provided context.\n<|user|>\nContext:\n<PASSAGE>\n\nQuestion: <Q>\n<|assistant|>\n")
ids = tok(prompt, return_tensors="pt", add_special_tokens=False).input_ids
print(tok.decode(model.generate(ids, max_new_tokens=120, repetition_penalty=1.3)[0], skip_special_tokens=True))

Small base model: use a context for grounded answers; generations may be imperfect.

Downloads last month: 154

Safetensors

Model size

0.1B params

Tensor type

F32