Instructions to use kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16 with Transformers:

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

pipe = pipeline("image-text-to-text", model="kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16")
model = AutoModelForMultimodalLM.from_pretrained("kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16

SGLang

How to use kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16 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 "kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16" \
    --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": "kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16" \
        --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": "kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16 with Docker Model Runner:
```
docker model run hf.co/kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16
```

Gemma 4 31B Tamil + Devanagari OCR — BF16

This is the primary-quality merged checkpoint produced by the workspace's Tamil and Devanagari OCR fine-tune. It starts from google/gemma-4-31B-it and merges the selected rank-32 language-layer LoRA into Google's original BF16 weights. The vision tower stayed frozen. Sanskrit is covered where it is written in Devanagari; this model has not been validated for other Sanskrit scripts such as Grantha.

Training

Distillation dataset: kailasa-ngpt/gemini-3.7-flash-ocr-26-aug-2026
Target rows: 8,374 Devanagari and 4,066 Tamil; 68 Telugu rows excluded
Balanced training stream: 16,748 examples through deterministic Tamil oversampling
Optimized examples: 4,000 (1,000 steps, physical batch 4)
QLoRA: NF4 load, rank/alpha 32/32, 410 language-layer targets
Learning rate: 1e-4 cosine; best checkpoint at step 950
Best clean-book validation loss: 0.407109946
Sequence/image budgets: 8,192 total tokens and 1,120 vision tokens
Training peak: 31.13 GiB allocated on one RTX PRO 6000 96GB

Evaluation

All text metrics preserve raw model Unicode and line boundaries. The primary metric is extended-grapheme-cluster CER (gCER).

Gate	gCER mean	gCER median	gCER clipped at 100%	Catastrophic	4,096-token caps
Independent 80-page gate	25.68%	11.12%	17.42%	7/80	4/80
Untouched base, same pages	374.74%	17.56%	25.99%	11/80	6/80

The fine-tune beat the base on 66/80 paired pages. A 20,000-replicate, script-stratified bootstrap estimated 99.505% probability that its raw mean gCER is lower; the very wide interval is caused by unbounded CER on base-model repetition loops.

On the untouched public benchmark's 350 natural-text cases, this BF16 artifact scored 3.238% gCER (Tamil 5.512%, Devanagari 0.965%) and 53.14% exact match. Its aggregate gCER difference from the base was not statistically resolved on that short-text benchmark.

vLLM

From the workspace root:

scripts/serve_vllm.sh artifacts/gemma4-31b-tamil-devanagari-ocr-bf16
.venv-serve/bin/python scripts/ocr_vllm_client.py page.png --output page.txt

The client uses the exact training prompt, temperature-zero decoding, preserves output verbatim, and cancels long exact grapheme repetition cycles. Exit code 2 means the token limit was reached; exit code 3 means the repetition guard fired. The artifact pins the 1,120-token image budget in both model and processor configuration, so ordinary vLLM loading matches the fine-tuning input budget.

Limitations and terms

The source dataset card declares license other, and its labels are Gemini teacher outputs rather than human ground truth. It also documents teacher-side normalization. Review the source-corpus rights, dataset terms, Gemini terms, and the base model's Apache 2.0 license before redistribution or commercial deployment. OCR errors, including occasional autoregressive loops, remain; do not treat the output as a faithful scholarly edition without review.

Downloads last month: 9

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for kailasa-ngpt/gemma-4-31b-tamil-devanagari-ocr-bf16

Base model

google/gemma-4-31B

Finetuned

google/gemma-4-31B-it

Finetuned

(329)

this model