Instructions to use sunilprakash/Srstilm-Indic-4B-CPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sunilprakash/Srstilm-Indic-4B-CPT with Transformers:

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

pipe = pipeline("text-generation", model="sunilprakash/Srstilm-Indic-4B-CPT")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("sunilprakash/Srstilm-Indic-4B-CPT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sunilprakash/Srstilm-Indic-4B-CPT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sunilprakash/Srstilm-Indic-4B-CPT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sunilprakash/Srstilm-Indic-4B-CPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sunilprakash/Srstilm-Indic-4B-CPT

SGLang

How to use sunilprakash/Srstilm-Indic-4B-CPT 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 "sunilprakash/Srstilm-Indic-4B-CPT" \
    --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": "sunilprakash/Srstilm-Indic-4B-CPT",
		"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 "sunilprakash/Srstilm-Indic-4B-CPT" \
        --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": "sunilprakash/Srstilm-Indic-4B-CPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sunilprakash/Srstilm-Indic-4B-CPT with Docker Model Runner:
```
docker model run hf.co/sunilprakash/Srstilm-Indic-4B-CPT
```

Srstilm-Indic-4B-CPT

Indic QLoRA continued-pretrain of Qwen3.5-4B-Base with a +29K-token Indic tokenizer extension (277K vocab). Trained ~13M tokens on a 400K-sequence Indic+code+English corpus (50/30/20); embeddings frozen, LoRA on attn/MLP. On held-out Indic text it lowers loss 9.16 to 6.96 (24%) vs the extended-vocab base. Cost-effective experimental build. Use with the extended tokenizer in this repo.

Model

License: apache-2.0
Method: continued pretraining with an extended tokenizer (+Indic merges), Sailor new-row embedding init, clean base-row freeze.
Languages: hi, mr, ta, te, kn, sa, en

Evaluation

Benchmark	Score
Held-out Indic loss (base + extended tokenizer)	9.16
Held-out Indic loss (this model, + LoRA)	6.96
Held-out Indic loss reduction (%)	24

Intended use & limitations

Research / Indic + code generation. As a continued-pretrained base it inherits Qwen/Qwen3.5-4B-Base's strengths and biases; evaluate before production use.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for sunilprakash/Srstilm-Indic-4B-CPT

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

(92)

this model