Instructions to use TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft with Transformers:

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

pipe = pipeline("text-generation", model="TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft")
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("TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft")
model = AutoModelForMultimodalLM.from_pretrained("TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft

SGLang

How to use TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft 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 "TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft" \
    --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": "TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft",
		"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 "TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft" \
        --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": "TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft with Docker Model Runner:
```
docker model run hf.co/TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft
```

HopCoder Mini 35B A3B VL36 Full-SFT

Endpoint-ready full-SFT checkpoint. The training export was repacked into the base model serving key layout with packed MoE expert tensors.

Use Transformers >=5.5.0 for qwen3_5_moe support. vLLM images that ship older Transformers may fail unless configured to use a new enough Transformers backend.

Featherless Compatibility

This repo is prepared for the Featherless Hugging Face ingestion requirements:

Full model weights, not LoRA or QLoRA adapters.
Safetensors shards with model.safetensors.index.json.
Export dtype: FP16.
Tensor names and shapes are validated against TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36; no embedding resize or tensor-shape variation is introduced.
Model card is present in this repository.

Featherless serves Qwen-family models at up to 16k context. The source config may advertise a larger native context, but prompts plus completions should stay within Featherless' served context limit.

Tool Calling

The tokenizer chat template is included in tokenizer_config.json and chat_template.jinja. Tool calls are trained and documented as JSON inside <tool_call> tags:

<tool_call>
{"name":"tool_name","arguments":{"argument_name":"value"}}
</tool_call>

After a <tool_response> turn, clients should continue generation until the assistant provides a final answer.

Downloads last month: 20

Safetensors

Model size

35B params

Tensor type

F16

Model tree for TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36-fullsft

Base model

TaimoorSiddiqui/HopCoder-Mini-35B-A3B-VL36

Finetuned

(1)

this model