Instructions to use Jaidchen/Focus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jaidchen/Focus with Transformers:

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

pipe = pipeline("text-generation", model="Jaidchen/Focus")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jaidchen/Focus")
model = AutoModelForCausalLM.from_pretrained("Jaidchen/Focus")
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 Jaidchen/Focus with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Jaidchen/Focus

SGLang

How to use Jaidchen/Focus 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 "Jaidchen/Focus" \
    --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": "Jaidchen/Focus",
		"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 "Jaidchen/Focus" \
        --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": "Jaidchen/Focus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jaidchen/Focus with Docker Model Runner:
```
docker model run hf.co/Jaidchen/Focus
```

Focus

repackaged Qwen 3.6 27B with a simplified architecture and minor opinionated improvements

all vision-related components removed
reduced storage and memory, faster inference
zero loss of output quality

comparison

	Qwen 3.6 27B	Focus
author	Alibaba Qwen	Jaid
repository	Qwen/Qwen3.6-27B	Jaidchen/Focus
architecture	`qwen3_5`	`qwen3_5_text`
Transformers handler	`Qwen3_5ForConditionalGeneration`	`Qwen3_5ForCausalLM`
tensor entries	1199	866
tensor type	bf16	bf16
parameters	27 781 427 952	27 320 697 856
vocabulary size	248 320	248 320
context size	262 144	262 144
MTP	integrated	integrated
sampling strategy	random sampling	greedy/deterministic
sampling parameters	do_sample: true temperature: 0.6 top_k: 20 top_p: 0.95	do_sample: false
input modality	text, image, video	text
repository size	55 586 101 650	54 664 408 333
model size	55 562 855 904	54 641 395 712
splits	11	none
Jinja template	Qwen original	Qwen original + Unsloth tweaks + custom unimodality patch

pros

reduced storage needs
reduced loading time
reduced VRAM occupancy, thus more room for context
increased inference speed
simplified architecture, unlocking some further potential for optimizing low-level procedures

cons

legally blind
- Pictures and video frames can still be present in the context without crashing, but their contents are no longer interpreted by the model and won’t do anything else than waste space.
- If you occasionally rely on those capabilities, I suggest adding a consult tool to your harness that calls a vision-enabled subagent model like Gemini Flash or GPT.
reduced compatibility
- The applied coercions may confuse your inference engine in case it has fixed expectations about the model’s architecture and thus lead to unpredictable behavior.
- The simplified architecture is handled by the Qwen3_5ForCausalLM class which may not be included in your inference engine. In this case you would need to ask your agent or integrate it yourself.

caveats

model file not split, possibly causing issues if intended to be stored on an HDD from the previous century
random sampling disabled by default, less suitable for long-form writing, entertainment and casual chat

license

Apache 2.0, derived from Qwen 3.6 27B

Downloads last month: 2,515

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for Jaidchen/Focus

Base model

Qwen/Qwen3.6-27B

Finetuned

(290)

this model