Instructions to use Hellohihihih/qwen35-v35-textmix-merged-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hellohihihih/qwen35-v35-textmix-merged-full with Transformers:

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

pipe = pipeline("text-generation", model="Hellohihihih/qwen35-v35-textmix-merged-full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Hellohihihih/qwen35-v35-textmix-merged-full")
model = AutoModelForCausalLM.from_pretrained("Hellohihihih/qwen35-v35-textmix-merged-full", 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 Hellohihihih/qwen35-v35-textmix-merged-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hellohihihih/qwen35-v35-textmix-merged-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hellohihihih/qwen35-v35-textmix-merged-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hellohihihih/qwen35-v35-textmix-merged-full

SGLang

How to use Hellohihihih/qwen35-v35-textmix-merged-full 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 "Hellohihihih/qwen35-v35-textmix-merged-full" \
    --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": "Hellohihihih/qwen35-v35-textmix-merged-full",
		"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 "Hellohihihih/qwen35-v35-textmix-merged-full" \
        --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": "Hellohihihih/qwen35-v35-textmix-merged-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Hellohihihih/qwen35-v35-textmix-merged-full with Docker Model Runner:
```
docker model run hf.co/Hellohihihih/qwen35-v35-textmix-merged-full
```

qwen35-v35-textmix-merged-full

This is a full merged model made by merging:

Base model: Qwen/Qwen3.5-9B
LoRA adapter: Hellohihihih/qwen35-v30-textmix-lora

What this is

Full merged causal language model
TextMix LoRA merged into base weights
No PEFT adapter loading required at inference time

What this is not

Not an omni model
No image/audio/video encoder
No multimodal projector

Prompt format

Fast mode:

<|mode_fast|>
### User:
...
### Assistant:
<|answer|>
...
</answer>

Thinking mode:

<|mode_think|>
### User:
...
### Assistant:
<|think|>
...
</think>
<|answer|>
...
</answer>

Downloads last month: 5

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for Hellohihihih/qwen35-v35-textmix-merged-full

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(721)

this model