Qwen3-thirukkural-tamil-v2/README.md

library_name, license, base_model, tags, model-index

library_name	license	base_model	tags	model-index
transformers	apache-2.0	Qwen/Qwen3-0.6B	generated_from_trainer	name results Qwen3-thirukkural-tamil-v2

Qwen3-thirukkural-tamil-v2

This model is a fine-tuned version of Qwen/Qwen3-0.6B on an Thirukkural dataset. It achieves the following results on the evaluation set:

• Loss: 0.2986

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 2
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss
0.2331	1.0	200	0.3307
0.1840	2.0	400	0.3093
0.1735	3.0	600	0.3013
0.1550	4.0	800	0.2983
0.1789	5.0	1000	0.2980
0.1689	6.0	1200	0.2986

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "tidelganesh/Qwen3-thirukkural-tamil"  # your repo
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, dtype="auto")

messages = [{"role": "user", "content": "பொறையுடைமை அதிகாரத்தில் வரும் 158ஆம் குறளைத் தருக."}]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

output = model.generate(
    **inputs, max_new_tokens=150,
    eos_token_id=tokenizer.eos_token_id,
    pad_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Framework versions

• Transformers 5.14.1
• Pytorch 2.8.0+cu128
• Datasets 5.0.0
• Tokenizers 0.22.2