Instructions to use sugiv/qwen3-8b-tanglish with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sugiv/qwen3-8b-tanglish with Transformers:

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

pipe = pipeline("text-generation", model="sugiv/qwen3-8b-tanglish")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sugiv/qwen3-8b-tanglish")
model = AutoModelForCausalLM.from_pretrained("sugiv/qwen3-8b-tanglish", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sugiv/qwen3-8b-tanglish with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sugiv/qwen3-8b-tanglish"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sugiv/qwen3-8b-tanglish",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sugiv/qwen3-8b-tanglish

SGLang

How to use sugiv/qwen3-8b-tanglish 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 "sugiv/qwen3-8b-tanglish" \
    --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": "sugiv/qwen3-8b-tanglish",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "sugiv/qwen3-8b-tanglish" \
        --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": "sugiv/qwen3-8b-tanglish",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sugiv/qwen3-8b-tanglish with Docker Model Runner:
```
docker model run hf.co/sugiv/qwen3-8b-tanglish
```

Qwen3-8B · Tanglish LoRA v1

Fine-tune of Qwen/Qwen3-8B that replies in casual Tanglish — code-mixed Tamil transliterated into the Latin alphabet, as spoken every day in Chennai and across South India.

Trained on sugiv/tanglish-pairs-v1 (81,261 SFT examples) with LoRA r=16, alpha=32 on the bf16 base (not QLoRA/4-bit — L40S 48 GB has enough VRAM for cleaner training). This repo ships the fully merged bf16 model (16.4 GB) plus a standalone PEFT adapter and all 27 intermediate resume checkpoints.

Highlights (from Phase 4 eval)

Beats stock Qwen3-8B on every LLM-judge dimension on both single-turn and multi-turn Tanglish prompts. Full report at eval/PHASE_4_EVAL.md.
Judge: qwen3-235b-a22b-instruct-2507, temperature=0, 40/40 parses successful.

Dimension (1-5, higher = better)	tng	base	delta
single-turn intelligibility	4.87	4.20	+0.67
single-turn tanglish_authenticity	4.33	3.00	+1.33
single-turn helpfulness	4.00	3.33	+0.67
single-turn naturalness	4.60	3.53	+1.07
multi-turn intelligibility	5.00	4.80	+0.20
multi-turn tanglish_authenticity	4.00	3.60	+0.40
multi-turn helpfulness	4.60	3.60	+1.00
multi-turn naturalness	4.80	4.00	+0.80

7.5x faster inference than base: 1.91 s vs 14.39 s mean single-turn on L4. Base emits a <think>Okay, the user is asking...</think> reasoning dump on every casual chat; this fine-tune was trained on outputs that keep <think></think> empty so it goes straight to the Tanglish reply.
Zero Tamil-script leaks on 15 held-out prompts (base has 3/15).

Training (verified from `training/qwen_train.log` + `trainer_state.json`)

Setting	Value
Base model	`Qwen/Qwen3-8B` (bf16, flash_attention_2, gradient_checkpointing)
Adapter	LoRA r=16, alpha=32, target = all-linear
Precision	bf16 (not QLoRA / 4-bit)
Corpus	sugiv/tanglish-pairs-v1, 77,198 train + 4,063 val
Effective batch size	32 (per-device 4 x grad-accum 8)
Learning rate	2e-4 cosine, warmup steps = 100
Total training steps	~14,475 (3 full epochs, last saved checkpoint at 13,500)
Best `eval_loss`	0.8126 at step 13,500
First eval (step 500)	1.1184
Eval-loss trajectory	monotonically decreasing across all 27 checkpoints
Optimizer	AdamW
Hardware	1x L40S 48 GB SECURE (RunPod, US-KS-1)
Wall time	~11 hours
Cost	~$13.36

Full step-by-step training log at training/qwen_train.log (2.1 MB, 702 log entries). Config at training/qwen_train_tanglish.yaml.

Usage

Merged model (recommended, no PEFT install needed)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "sugiv/qwen3-8b-tanglish",
    torch_dtype="bfloat16",
    device_map="cuda",
    token="hf_...",
)
tok = AutoTokenizer.from_pretrained("sugiv/qwen3-8b-tanglish", token="hf_...")

msgs = [
    {"role": "system", "content": "You are a friendly Tanglish-speaking assistant. Reply naturally in casual, code-mixed Tanglish..."},
    {"role": "user", "content": "machi, nalaikku Chennai la enna weather?"},
]
prompt = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to("cuda")
out = model.generate(prompt, max_new_tokens=200, temperature=0.7, top_p=0.9, do_sample=True)
print(tok.decode(out[0][prompt.shape[-1]:], skip_special_tokens=True))
# => 'da, innum hot ah iruku, morning la 28 degree nu solraanga.'

LoRA adapter (attach to a stock Qwen3-8B)

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", torch_dtype="bfloat16", device_map="cuda")
model = PeftModel.from_pretrained(base, "sugiv/qwen3-8b-tanglish", subfolder="lora", token="hf_...")

vLLM / RunPod Serverless (production)

# On Runpod Hub: pick `runpod-workers/worker-vllm`, set:
#   MODEL_NAME     = sugiv/qwen3-8b-tanglish
#   DTYPE          = bfloat16
#   MAX_MODEL_LEN  = 2048
#   HF_TOKEN       = hf_...
# GPU: L40S 48 GB SECURE recommended (fits with headroom).

Resume from any of the 27 intermediate checkpoints

Every checkpoint under checkpoints/checkpoint-{500,1000,...,13500}/ contains the LoRA adapter, optimizer state, LR scheduler state, RNG state, and trainer_state.json — enough to resume TRL SFTTrainer from that exact step.

Repo contents

Path	Bytes	What
`model-000{1..4}-of-00004.safetensors`	~16.4 GB	Merged bf16 weights (base + LoRA collapsed)
`config.json` + `tokenizer*` + `chat_template.jinja`	~14 MB	Same as base Qwen3-8B, unmodified
`lora/adapter_model.safetensors`	~175 MB	LoRA-only best adapter (step 13500)
`lora/{adapter_config,training_args,tokenizer*}`	~14 MB	PEFT metadata + tokenizer
`checkpoints/checkpoint-*/`	~14 GB (27 dirs)	Resume checkpoints every 500 steps, includes optimizer.pt + scheduler.pt
`eval/MANIFEST.json`	~80 KB	40 records with LLM-judge scores across 4 dimensions
`eval/PHASE_4_EVAL.md`	~6 KB	Human-readable eval report with side-by-side samples
`training/qwen_train.log`	~2 MB	Full stdout from the 11-hour training run
`training/*.yaml`	~5 KB	Training config used

Known limitations

Soft-refusal on safety: the model deflects "how do I hack a database" with playful Tanglish banter instead of a textbook refusal. Judge deducts helpfulness=1 but flags the response as safe. If you need a stricter tone, layer a system-prompt refusal template at the agent layer.
Verbose reasoning mode is trained out: the base Qwen3-8B emits <think>...</think> reasoning blocks on casual chat, and this fine-tune suppresses that behaviour. If you want explicit reasoning, use the base model — this one goes straight to the answer.
Language support: Tanglish (Latin-script Tamil + English code-mix) is the trained target. It can still reply in pure Tamil script or pure English if prompted, but the training corpus is 100% transliterated Tanglish.

License

Apache-2.0 (inherited from Qwen/Qwen3-8B). Commercial use allowed. Attribution to both this repo and the base model is appreciated.

Citation

@misc{tanglish_qwen3_2026,
  title={Qwen3-8B Tanglish LoRA},
  author={sugiv},
  year={2026},
  url={https://huggingface.co/sugiv/qwen3-8b-tanglish}
}

Companion training corpus: sugiv/tanglish-pairs-v1
Companion voice TTS: sugiv/fish-speech-1.5-tanglish
Underlying audio dataset: sugiv/tanglish-audio-v1
Base model: Qwen/Qwen3-8B

Downloads last month: 97

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for sugiv/qwen3-8b-tanglish

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Adapter

(2169)

this model

sugiv
/

qwen3-8b-tanglish

Qwen3-8B · Tanglish LoRA v1

Highlights (from Phase 4 eval)

Training (verified from `training/qwen_train.log` + `trainer_state.json`)

Usage

Merged model (recommended, no PEFT install needed)

LoRA adapter (attach to a stock Qwen3-8B)

vLLM / RunPod Serverless (production)

Resume from any of the 27 intermediate checkpoints

Repo contents

Known limitations

License

Citation

Related

Model tree for sugiv/qwen3-8b-tanglish

Qwen3-8B · Tanglish LoRA v1

Highlights (from Phase 4 eval)

Training (verified from training/qwen_train.log + trainer_state.json)

Usage

Merged model (recommended, no PEFT install needed)

LoRA adapter (attach to a stock Qwen3-8B)

vLLM / RunPod Serverless (production)

Resume from any of the 27 intermediate checkpoints

Repo contents

Known limitations

License

Citation

Related

Model tree for sugiv/qwen3-8b-tanglish

Training (verified from `training/qwen_train.log` + `trainer_state.json`)