Instructions to use FINAL-Bench/Darwin-Chimera-4B-Gen1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Darwin-Chimera-4B-Gen1 with Transformers:

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

pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-Chimera-4B-Gen1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FINAL-Bench/Darwin-Chimera-4B-Gen1")
model = AutoModelForCausalLM.from_pretrained("FINAL-Bench/Darwin-Chimera-4B-Gen1", 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 FINAL-Bench/Darwin-Chimera-4B-Gen1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Darwin-Chimera-4B-Gen1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FINAL-Bench/Darwin-Chimera-4B-Gen1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-Chimera-4B-Gen1

SGLang

How to use FINAL-Bench/Darwin-Chimera-4B-Gen1 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 "FINAL-Bench/Darwin-Chimera-4B-Gen1" \
    --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": "FINAL-Bench/Darwin-Chimera-4B-Gen1",
		"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 "FINAL-Bench/Darwin-Chimera-4B-Gen1" \
        --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": "FINAL-Bench/Darwin-Chimera-4B-Gen1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINAL-Bench/Darwin-Chimera-4B-Gen1 with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Darwin-Chimera-4B-Gen1
```

Darwin-Chimera-4B-Gen1 / README.md

SeaWolf-AI

Gen1 backbone: Qwen3-4B attention healing (FFN frozen)

705321b verified about 2 months ago

preview code

Raw

History Blame Contribute Delete

2.73 kB

	---
	license: apache-2.0
	base_model:
	- Qwen/Qwen3-4B
	language:
	- ko
	- en
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- darwin
	- darwin-chimera
	- attention-healing
	- sliding-window
	- qwen3
	- vidraft
	- research-checkpoint
	---

	# Darwin-Chimera-4B-Gen1 (Backbone · Research)

	> ⚠️ Generation-1 backbone — a research checkpoint, not a product. Private repo.
	> This is a Qwen3-4B derivative, not a from-scratch model. We state this explicitly.

	## What this is

	`Darwin-Chimera-4B-Gen1` is the first-generation adapter backbone of the Darwin-Chimera
	line. We take Qwen/Qwen3-4B and re-wire only its attention via VIDRAFT
	attention-healing, while freezing the FFN, embeddings, and lm_head, and convert the
	attention to a sliding-window configuration.

	The purpose is to verify that a VIDRAFT-healed attention circuit can sit on a frozen
	knowledge core — the foundation for Generation-2 (FFN cross-breeding with other models).

	## Honest weight fingerprint (vs Qwen/Qwen3-4B)

	Measured relative change `\|\|A−B\|\| / \|\|A\|\|` against the original Qwen3-4B:

	\| Component \| Relative change \| Note \|
	\|-----------\|:---:\|------\|
	\| FFN (mlp) \| 0.000% \| frozen — identical to Qwen3-4B \|
	\| embed / lm_head \| 0.000% \| frozen — identical \|
	\| attention (self_attn) \| 3.0% mean (7.5% max) \| healed \|
	\| layernorm \| 0.04% \| minimal \|
	\| config (hidden/inter/layers/vocab) \| identical \| only `sliding_window=4096` added \|

	→ At the weight level this checkpoint is clearly a Qwen3-4B derivative. We make no
	claim of independence or from-scratch training. Knowledge/FFN is 100% Qwen3-4B.

	## Training

	- Method: attention-only healing (self_attn + per-layer norms trainable; FFN/embed/lm_head frozen)
	- Attention: full → sliding window (4096), 5:1 sliding:full layer ratio
	- Tokens: ~3B (Korean-centric annealing mix)
	- Base: Qwen/Qwen3-4B (Apache 2.0)

	## Evaluation (base, zero-shot — reference only)

	- Generation: 6/6 domains coherent (Korean / English / science / code / math / biology), no gibberish
	- KMMLU (6 subjects, 240Q, zero-shot, greedy): 27.1% vs Qwen3-4B base 13.3% (same protocol, +13.8pp)
	- Absolute KMMLU is low because this is a base (non-instruct) checkpoint; instruction-following
	and benchmark quality are expected to come from a later SFT stage. The comparison above is a
	same-condition relative measurement, not an absolute SOTA claim.

	## Intended use

	- Backbone for Darwin-Chimera Generation-2 (cross-architecture FFN cross-breeding research)
	- Research and experimentation only. Not for production.

	## License & attribution

	Apache 2.0, inherited from Qwen/Qwen3-4B. Built on Qwen/Qwen3-4B.