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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jaidchen/Focus")
model = AutoModelForCausalLM.from_pretrained("Jaidchen/Focus", 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=256)
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 Aug 9

Commit

79a9f3e

verified ·

1 Parent(s): b0d5548

Update README.md

Browse files

Files changed (1) hide show

README.md +26 -21

README.md CHANGED Viewed

@@ -165,30 +165,35 @@ repackaged [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.6-27B) with a simpli
 ## Jinja template changes
-- base: [Qwen original](https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/chat_template.jinja)
-- adopted tweaks from [Unsloth version](https://huggingface.co/unsloth/Qwen3.5-27B/blob/main/chat_template.jinja)
-  - Added `developer` role as alias for `system`. ([line 45–57](https://huggingface.co/unsloth/Qwen3.5-27B/blob/909b2cc7dc1737891ad8f5a7213b702b39410e43/chat_template.jinja#L45-L57))
-  - Merged all leading system/developer messages into a single policy message. ([line 58–75](https://huggingface.co/unsloth/Qwen3.5-27B/blob/909b2cc7dc1737891ad8f5a7213b702b39410e43/chat_template.jinja#L58-L75))
-  - Allowed histories without a normal human query. ([line 76–87](https://huggingface.co/unsloth/Qwen3.5-27B/blob/909b2cc7dc1737891ad8f5a7213b702b39410e43/chat_template.jinja#L76-L87))
-  - Retained later system/developer messages as policy messages. ([line 87–89](https://huggingface.co/unsloth/Qwen3.5-27B/blob/909b2cc7dc1737891ad8f5a7213b702b39410e43/chat_template.jinja#L87-L89), [line 147–149](https://huggingface.co/unsloth/Qwen3.5-27B/blob/909b2cc7dc1737891ad8f5a7213b702b39410e43/chat_template.jinja#L147-L149))
-  - Made mapping-argument rendering portable by avoiding `|items`. ([line 108–133](https://huggingface.co/unsloth/Qwen3.5-27B/blob/909b2cc7dc1737891ad8f5a7213b702b39410e43/chat_template.jinja#L108-L133), [line 122–130](https://huggingface.co/unsloth/Qwen3.5-27B/blob/909b2cc7dc1737891ad8f5a7213b702b39410e43/chat_template.jinja#L122-L130))
 - adopted tweaks from [Froggeric version](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja)
-  - Added `preserve_thinking` option to retain historical reasoning. ([line 8](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L8), [line 225–230](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L225-L230))
-  - Retained mid-conversation system/developer messages as Qwen system turns. ([line 165–182](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L165-L182), [line 167–180](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L167-L180))
-  - Allowed string-valued `message.thinking` as fallback for historical reasoning. ([line 183–197](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L183-L197))
-  - Applied boundary-aware `</think>` parsing. ([line 198–223](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L198-L223))
-  - Avoided synthesizing empty historical thinking blocks. ([line 225–230](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L225-L230))
-  - Supported both wrapped and direct tool calls, but never null-wrapped. ([line 231–237](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L231-L237))
-  - Preserved non-empty string tool arguments. ([line 261–280](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L261-L280), [line 277–279](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L277-L279))
-  - Used direct message indexing for tool-response grouping instead of `loop.previtem`/`loop.nextitem`. ([line 165](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L165), [line 286–318](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L286-L318))
 - custom tweaks
-  - Merged any number of leading system/developer messages, not just two.
-  - Applied boundary-aware `</think>` parsing but excluded malformed-tag recovery.
-  - Raised an error for unknown roles instead of silently omitting or converting them.
-  - Used direct message indexing for tool-response grouping without Froggeric’s error-escalation state.
 - unimodality patch
-  - Rendered image and video content as `[image]` and `[video]`.
 ## license
-Apache 2.0 – inherited from [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/LICENSE)

 ## Jinja template changes
+`chat.jinja` is reproducibly built from an untouched upstream template plus the ordered patch stack in `jinja_build/`. `jinja_build/build.ps1` applies the patches lexicographically and overwrites the final `chat.jinja`.
+- base: [Qwen/Qwen3.6-27B original](https://huggingface.co/Qwen/Qwen3.6-27B/blob/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9/chat_template.jinja)
+  - commit `6a9e13bd6fc8f0983b9b99948120bc37f49c13e9`
+  - SHA-256 `E84F32A23FDDA27689F868AA4A1A5621F41133E51A48D7F3EFCBEA2839574259`
+- adopted tweaks from [Unsloth Qwen3.6](https://huggingface.co/unsloth/Qwen3.6-27B/blob/d6e694245c1d535508bc54062f5e258d7b1e04f5/chat_template.jinja)
+  - Added `developer` role as alias for `system`. ([lines 45–57](https://huggingface.co/unsloth/Qwen3.6-27B/blob/d6e694245c1d535508bc54062f5e258d7b1e04f5/chat_template.jinja#L45-L57))
+  - Merged leading system/developer messages into a single policy message. ([lines 45–57](https://huggingface.co/unsloth/Qwen3.6-27B/blob/d6e694245c1d535508bc54062f5e258d7b1e04f5/chat_template.jinja#L45-L57), [lines 67–75](https://huggingface.co/unsloth/Qwen3.6-27B/blob/d6e694245c1d535508bc54062f5e258d7b1e04f5/chat_template.jinja#L67-L75))
+  - Allowed histories without a normal human query. ([lines 76–86](https://huggingface.co/unsloth/Qwen3.6-27B/blob/d6e694245c1d535508bc54062f5e258d7b1e04f5/chat_template.jinja#L76-L86))
+  - Made mapping-argument rendering portable by avoiding `|items`. ([lines 122–130](https://huggingface.co/unsloth/Qwen3.6-27B/blob/d6e694245c1d535508bc54062f5e258d7b1e04f5/chat_template.jinja#L122-L130))
 - adopted tweaks from [Froggeric version](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja)
+  - Added `preserve_thinking` option to retain historical reasoning. ([line 8](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L8), [lines 225–230](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L225-L230))
+  - Retained mid-conversation system/developer messages as Qwen system turns. ([lines 165–182](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L165-L182))
+  - Allowed string-valued `message.thinking` as fallback for historical reasoning. ([lines 183–197](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L183-L197))
+  - Applied boundary-aware `</think>` parsing. ([lines 198–223](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L198-L223))
+  - Avoided synthesizing empty historical thinking blocks. ([lines 225–230](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L225-L230))
+  - Supported both wrapped and direct tool calls, but never null-wrapped. ([lines 231–237](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L231-L237))
+  - Preserved non-empty string tool arguments. ([lines 261–280](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L261-L280))
+  - Used direct message indexing for tool-response grouping instead of `loop.previtem`/`loop.nextitem`. ([line 165](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L165), [lines 286–318](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L286-L318))
 - custom tweaks
+  - Merged any number of leading system/developer messages, generalizing Unsloth's two-message merge. ([lines 45–57](https://huggingface.co/unsloth/Qwen3.6-27B/blob/d6e694245c1d535508bc54062f5e258d7b1e04f5/chat_template.jinja#L45-L57))
+  - Applied boundary-aware `</think>` parsing but excluded Froggeric's malformed-tag recovery. ([lines 198–223](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L198-L223))
+  - Raised an error containing the offending role instead of Qwen's generic unknown-role error. ([lines 143–144](https://huggingface.co/Qwen/Qwen3.6-27B/blob/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9/chat_template.jinja#L143-L144))
+  - Used direct message indexing for tool-response grouping without Froggeric's error-escalation state. ([lines 286–318](https://huggingface.co/froggeric/Qwen-Fixed-Chat-Templates/blob/b225c1d63f84c65af7dd6af2ba384eb037aa885e/chat_template.jinja#L286-L318))
+  - Guarded undefined `tools`/`tool_calls` and handled non-mapping content items defensively.
+  - Adopted Qwen's proposed `continue_final_message` fix for partial assistant prefills. ([lines 130–132](https://huggingface.co/Qwen/Qwen3.6-27B/blob/0774bb84a25294dac0538c2bfc7abc08ae89d522/chat_template.jinja#L130-L132))
 - unimodality patch
+  - Removed Qwen's vision-token machinery and rendered image/video content as `[image]` and `[video]`. ([lines 1–41](https://huggingface.co/Qwen/Qwen3.6-27B/blob/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9/chat_template.jinja#L1-L41))
 ## license
+Apache 2.0 – inherited from [Qwen 3.6 27B](https://huggingface.co/Qwen/Qwen3.6-27B/blob/main/LICENSE)