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
```

Jaidchen commited on 11 days ago

Commit

72699aa

verified ·

1 Parent(s): 2e50e7d

Update README.md

Browse files

Files changed (1) hide show

README.md +16 -6

README.md CHANGED Viewed

@@ -6,6 +6,10 @@ base_model: Qwen/Qwen3.6-27B
 pipeline_tag: text-generation
 ---
 # Focus
 repackaged [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.6-27B) with a simplified architecture and minor opinionated improvements
@@ -42,7 +46,7 @@ repackaged [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.6-27B) with a simpli
   <td>1199</td>
   <td>866</td>
 </tr>
-<tr style='background: rgb(from currentColor r g b / 10%); color: rgb(from currentColor r g b / 60%)'>
   <td>tensor type</td>
   <td>bf16</td>
   <td>bf16</td>
@@ -52,17 +56,17 @@ repackaged [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.6-27B) with a simpli
   <td>27 781 427 952</td>
   <td>27 320 697 856</td>
 </tr>
-<tr style='background: rgb(from currentColor r g b / 10%); color: rgb(from currentColor r g b / 60%)'>
   <td>vocabulary size</td>
   <td>248 320</td>
   <td>248 320</td>
 </tr>
-<tr style='background: rgb(from currentColor r g b / 10%); color: rgb(from currentColor r g b / 60%)'>
   <td>context size</td>
   <td>262 144</td>
   <td>262 144</td>
 </tr>
-<tr style='background: rgb(from currentColor r g b / 10%); color: rgb(from currentColor r g b / 60%)'>
   <td>MTP</td>
   <td>integrated</td>
   <td>integrated</td>
@@ -131,9 +135,15 @@ repackaged [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.6-27B) with a simpli
 - 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](https://openrouter.ai/~google/gemini-flash-latest) or [GPT](https://openrouter.ai/~openai/gpt-latest).
-- 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.
 - model file not split, possibly causing issues if intended to be stored on an HDD from the previous century
 ## license
-Apache 2.0, derived from [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/LICENSE)

 pipeline_tag: text-generation
 ---
+<center>
+<img style='height: 16em' src='https://cdn-uploads.huggingface.co/production/uploads/63e9a1c4ccae1fe5c622b9f6/ADYJx3gsTmTVPuhHGMM5S.webp'/>
+</center>
 # Focus
 repackaged [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.6-27B) with a simplified architecture and minor opinionated improvements
   <td>1199</td>
   <td>866</td>
 </tr>
+<tr style='background: rgb(from currentColor r g b / 10%); color: rgb(from currentColor r g b / 10%)'>
   <td>tensor type</td>
   <td>bf16</td>
   <td>bf16</td>
   <td>27 781 427 952</td>
   <td>27 320 697 856</td>
 </tr>
+<tr style='background: rgb(from currentColor r g b / 10%); color: rgb(from currentColor r g b / 10%)'>
   <td>vocabulary size</td>
   <td>248 320</td>
   <td>248 320</td>
 </tr>
+<tr style='background: rgb(from currentColor r g b / 10%); color: rgb(from currentColor r g b / 10%)'>
   <td>context size</td>
   <td>262 144</td>
   <td>262 144</td>
 </tr>
+<tr style='background: rgb(from currentColor r g b / 10%); color: rgb(from currentColor r g b / 10%)'>
   <td>MTP</td>
   <td>integrated</td>
   <td>integrated</td>
 - 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](https://openrouter.ai/~google/gemini-flash-latest) or [GPT](https://openrouter.ai/~openai/gpt-latest).
+- 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](https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/LICENSE)