Instructions to use Timegravity/tamil-lm-2b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Timegravity/tamil-lm-2b-instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="Timegravity/tamil-lm-2b-instruct")
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("Timegravity/tamil-lm-2b-instruct")
model = AutoModelForMultimodalLM.from_pretrained("Timegravity/tamil-lm-2b-instruct", 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 Timegravity/tamil-lm-2b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Timegravity/tamil-lm-2b-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": "Timegravity/tamil-lm-2b-instruct",
		"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/Timegravity/tamil-lm-2b-instruct

SGLang

How to use Timegravity/tamil-lm-2b-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 "Timegravity/tamil-lm-2b-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": "Timegravity/tamil-lm-2b-instruct",
		"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 "Timegravity/tamil-lm-2b-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": "Timegravity/tamil-lm-2b-instruct",
		"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 Timegravity/tamil-lm-2b-instruct with Docker Model Runner:
```
docker model run hf.co/Timegravity/tamil-lm-2b-instruct
```

vignesh1234 commited on Sep 8

Commit

77f9509

verified ·

1 Parent(s): 6d7e6e4

Upload eval_results/sft_final_test.json with huggingface_hub

Browse files

Files changed (1) hide show

eval_results/sft_final_test.json +262 -0

eval_results/sft_final_test.json ADDED Viewed

	@@ -0,0 +1,262 @@

+[
+ {
+  "benchmark": "milu_ta",
+  "split": "test",
+  "n": 6372,
+  "metric": "acc",
+  "score": 0.2963,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T04:40:26",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "indicmmlu_pro_ta",
+  "split": "test",
+  "n": 12032,
+  "metric": "acc",
+  "score": 0.1232,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T05:46:08",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "belebele_ta",
+  "split": "test",
+  "n": 720,
+  "metric": "acc",
+  "score": 0.2472,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T05:47:40",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "include_ta",
+  "split": "test",
+  "n": 448,
+  "metric": "acc",
+  "score": 0.3371,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T05:48:37",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "mmlu_en",
+  "split": "test",
+  "n": 400,
+  "metric": "acc",
+  "score": 0.3575,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T05:49:30",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "gsm8k_en",
+  "split": "test",
+  "n": 160,
+  "metric": "acc",
+  "score": 0.0938,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T06:06:15",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "indicxnli_ta",
+  "split": "test",
+  "n": 5010,
+  "metric": "acc",
+  "score": 0.3513,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T06:14:16",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "indiccopa_ta",
+  "split": "test",
+  "n": 400,
+  "metric": "acc",
+  "score": 0.55,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T06:14:42",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "indicsentiment_ta",
+  "split": "test",
+  "n": 998,
+  "metric": "acc",
+  "score": 0.514,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T06:15:48",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "indicqa_ta",
+  "split": "test",
+  "n": 1022,
+  "metric": "f1",
+  "score": 0.1651,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T06:37:15",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "flores_en_ta",
+  "split": "test",
+  "n": 1012,
+  "metric": "chrf++",
+  "score": 43.6592,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T06:50:36",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "flores_en_ta",
+  "split": "test",
+  "n": 1012,
+  "metric": "bleu",
+  "score": 10.4105,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T06:50:36",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "flores_ta_en",
+  "split": "test",
+  "n": 1012,
+  "metric": "chrf++",
+  "score": 52.891,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T07:03:25",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "flores_ta_en",
+  "split": "test",
+  "n": 1012,
+  "metric": "bleu",
+  "score": 27.9848,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T07:03:25",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "in22gen_en_ta",
+  "split": "test",
+  "n": 820,
+  "metric": "chrf++",
+  "score": 37.2343,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T07:16:03",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "in22gen_en_ta",
+  "split": "test",
+  "n": 820,
+  "metric": "bleu",
+  "score": 5.5395,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T07:16:03",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "in22gen_ta_en",
+  "split": "test",
+  "n": 820,
+  "metric": "chrf++",
+  "score": 50.6845,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T07:28:32",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "in22gen_ta_en",
+  "split": "test",
+  "n": 820,
+  "metric": "bleu",
+  "score": 25.7654,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T07:28:32",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "xlsum_ta",
+  "split": "test",
+  "n": 2027,
+  "metric": "rougeL",
+  "score": 0.3038,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T09:01:46",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ },
+ {
+  "benchmark": "tanglish_heldout",
+  "split": "test",
+  "n": 2740,
+  "metric": "bpc",
+  "score": 3.2658,
+  "script": "eval/suite.py",
+  "commit": "814cd77",
+  "timestamp": "2026-09-07T09:03:24",
+  "stage": "sft_final",
+  "model": "ckpt/final/tamil-lm-2b-base",
+  "adapter": "ckpt/sft2/step_2468"
+ }
+]