Instructions to use Jun1801/telco-fc-m1b-qwen3-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jun1801/telco-fc-m1b-qwen3-4b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/workspace/models/Qwen3-4B")
model = PeftModel.from_pretrained(base_model, "Jun1801/telco-fc-m1b-qwen3-4b")

Transformers

How to use Jun1801/telco-fc-m1b-qwen3-4b with Transformers:

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

pipe = pipeline("text-generation", model="Jun1801/telco-fc-m1b-qwen3-4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Jun1801/telco-fc-m1b-qwen3-4b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jun1801/telco-fc-m1b-qwen3-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jun1801/telco-fc-m1b-qwen3-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jun1801/telco-fc-m1b-qwen3-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jun1801/telco-fc-m1b-qwen3-4b

SGLang

How to use Jun1801/telco-fc-m1b-qwen3-4b 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 "Jun1801/telco-fc-m1b-qwen3-4b" \
    --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": "Jun1801/telco-fc-m1b-qwen3-4b",
		"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 "Jun1801/telco-fc-m1b-qwen3-4b" \
        --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": "Jun1801/telco-fc-m1b-qwen3-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jun1801/telco-fc-m1b-qwen3-4b with Docker Model Runner:
```
docker model run hf.co/Jun1801/telco-fc-m1b-qwen3-4b
```

telco-fc-m1b-qwen3-4b / README.md

Jun1801

M1b SFT adapter — Qwen3-4B LoRA, 84.9% strict accuracy on real KPI eval

5bebe89 verified 4 months ago

preview code

Raw History Blame Contribute Delete

1.61 kB

	---
	library_name: peft
	base_model: Qwen/Qwen3-4B
	tags:
	- lora
	- sft
	- transformers
	- trl
	- function-calling
	- telco
	pipeline_tag: text-generation
	---

	# M1b — Telco Function Calling SFT (Qwen3-4B + LoRA)

	LoRA adapter fine-tuned on 26 real Viettel KPI functions (Vietnamese, read-only).

	## Results (1806 eval samples)

	\| Split \| Accuracy \|
	\|-------\|----------\|
	\| abstain \| 100.0% \|
	\| missing_slot \| 99.4% \|
	\| unseen \| 97.4% \|
	\| masked \| 94.6% \|
	\| seen \| 94.0% \|
	\| parallel \| 80.2% \|
	\| multi_step \| 54.3% \|
	\| Overall \| 84.9% \|

	## Usage

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer
	from peft import PeftModel

	base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B", torch_dtype="bfloat16", device_map="auto")
	model = PeftModel.from_pretrained(base, "Jun1801/telco-fc-m1b-qwen3-4b")
	tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B")
	```

	## Training

	- Base model: Qwen/Qwen3-4B
	- Dataset: [Jun1801/telco-fc-dataset](https://huggingface.co/datasets/Jun1801/telco-fc-dataset) — 7,526 samples (real KPI + warmup)
	- Method: SFT with TRL SFTTrainer, LoRA (r=16, alpha=32)
	- Epochs: 3, LR: 2e-4 (cosine decay)
	- Final train loss: 0.088 \| eval loss: 0.012
	- W&B: [run fhjp6hke](https://wandb.ai/tiendungcbh1801-hanoi-university-of-science-and-technology/telco-fc/runs/fhjp6hke)

	## Output format

	```json
	{"action": "call_function", "call": {"tool_name": "...", "arguments": {...}}}
	{"action": "call_functions", "calls": [{...}, ...]}
	{"action": "ask_clarification", "asked_slots": ["..."]}
	{"action": "abstain", "reason": "..."}
	```