Instructions to use kenpath/bhili_synthetic_qwen3.6_v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kenpath/bhili_synthetic_qwen3.6_v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="kenpath/bhili_synthetic_qwen3.6_v0.1")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("kenpath/bhili_synthetic_qwen3.6_v0.1")
model = AutoModelForMultimodalLM.from_pretrained("kenpath/bhili_synthetic_qwen3.6_v0.1", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kenpath/bhili_synthetic_qwen3.6_v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kenpath/bhili_synthetic_qwen3.6_v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kenpath/bhili_synthetic_qwen3.6_v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kenpath/bhili_synthetic_qwen3.6_v0.1

SGLang

How to use kenpath/bhili_synthetic_qwen3.6_v0.1 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 "kenpath/bhili_synthetic_qwen3.6_v0.1" \
    --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": "kenpath/bhili_synthetic_qwen3.6_v0.1",
		"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 "kenpath/bhili_synthetic_qwen3.6_v0.1" \
        --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": "kenpath/bhili_synthetic_qwen3.6_v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kenpath/bhili_synthetic_qwen3.6_v0.1 with Docker Model Runner:
```
docker model run hf.co/kenpath/bhili_synthetic_qwen3.6_v0.1
```

bhili_synthetic_qwen3.6_v0.1

Fine-tuned version of Qwen/Qwen3.6-27B for the Vistaar (unknown) use case.

Model Details

Base Model: Qwen/Qwen3.6-27B
Fine-tuning Method: LoRA (Low-Rank Adaptation)
Training Framework: HuggingFace Transformers + PEFT + DeepSpeed ZeRO-3
Merged: Full model weights (LoRA merged into base)

Training Configuration

LoRA Parameters

Parameter	Value
Rank (r)	64
Alpha	64
Dropout	0.1
Target Modules	['q_proj', 'k_proj', 'v_proj', 'o_proj', 'gate_proj', 'up_proj', 'down_proj']
Trainable Parameters	318,767,104 / 27,214,765,568 (1.1713%)

Training Hyperparameters

Parameter	Value
Epochs	1
Per-device Batch Size	1
Gradient Accumulation	8
Effective Batch Size	48
Learning Rate	2e-05
LR Scheduler	cosine
Warmup Ratio	N/A
Weight Decay	0.001
Max Grad Norm	1.0

Hardware & Performance

Metric	Value
GPUs	6x H100 80GB
Training Duration	1.10 hours
Final Training Loss	1.4863
Dataset Size	5,131 samples
Max Sequence Length	4096

W&B Run: https://wandb.ai/kenpath-ai-team/huggingface/runs/egljnf3k

Dataset

Name: synthetic-qwen3.6-bhili-synthetic
Samples Used: N/A

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "kenpath/bhili_synthetic_qwen3.6_v0.1",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("kenpath/bhili_synthetic_qwen3.6_v0.1")

messages = [
    {"role": "user", "content": "Your question here"}
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
).to(model.device)

output = model.generate(input_ids, max_new_tokens=512)
print(tokenizer.decode(output[0], skip_special_tokens=True))

License

This model inherits the license from the base model Qwen/Qwen3.6-27B.

Generated on 2026-06-04 06:31:57 | Merge took 2.9s

Downloads last month: 6

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for kenpath/bhili_synthetic_qwen3.6_v0.1

Base model

Qwen/Qwen3.6-27B

Adapter

(330)

this model