Instructions to use FINAL-Bench/Darwin-V9-Chimera-4B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Darwin-V9-Chimera-4B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-V9-Chimera-4B-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FINAL-Bench/Darwin-V9-Chimera-4B-SFT")
model = AutoModelForCausalLM.from_pretrained("FINAL-Bench/Darwin-V9-Chimera-4B-SFT", 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-V9-Chimera-4B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Darwin-V9-Chimera-4B-SFT"
# 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-V9-Chimera-4B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-V9-Chimera-4B-SFT

SGLang

How to use FINAL-Bench/Darwin-V9-Chimera-4B-SFT 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-V9-Chimera-4B-SFT" \
    --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-V9-Chimera-4B-SFT",
		"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-V9-Chimera-4B-SFT" \
        --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-V9-Chimera-4B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINAL-Bench/Darwin-V9-Chimera-4B-SFT with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Darwin-V9-Chimera-4B-SFT
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Darwin-V9-Chimera-4B-SFT (Generation 2 · instruction-tuned)

VIDRAFT attention + Qwen3-4B / Gemma4-E4B FFN crossbreed + SFT. A Qwen3-4B × Gemma4-E4B hybrid — NOT from-scratch. Private research checkpoint.

Lineage

Gen	Model	Composition
Gen1	Darwin-Chimera-4B-Gen1	Qwen3-4B attention-healing adapter
Gen2 (healed)	Darwin-V9-Chimera-4B	+ Gemma4-E4B FFN crossbreed → re-healing
Gen2 SFT (this)	Darwin-V9-Chimera-4B-SFT	+ B4-Hybrid SFT (think toggle + ko/en CoT)

SFT

data: B4_merged_hybrid, 17,202 ex (think/no_think toggle, Korean/English CoT)
method: ChatML + prompt masking (assistant-only loss) + full fine-tune, lr 2e-5, 3 epochs

Evaluation (KMMLU, ChatML)

measure	score
max_new=8 (short answer)	25.6% (measurement artifact)
max_new=768 (think)	52.2% (Math 70%, CS 67%)

→ With sufficient thinking budget, 52.2% — ~2× the healed checkpoint (27.8%). Instruction following is complete (think/no_think toggle, markdown, code). The short-answer score is an artifact: this model reasons before answering.

Weight fingerprint (honest)

vs Qwen3-4B: FFN 16% rel-change, attention 3%, embed 0.78%. FFN cosine 0.998 → Qwen-dominant.
vs Gemma4-E4B FFN: cosine 0.09 (15% blend, weak at weight level; Gemma knowledge partially visible in generation).
At the weight level this is clearly a Qwen3-4B derivative. We make no from-scratch / independence claim.

NEG (Native Entropy Gating)

A NEG-Head was trained (entropy-prediction pearson 0.92) and neg_modules.safetensors is included.
However, NEG showed no effect on KMMLU (threshold untuned / mid-difficulty). Potential effect on harder reasoning (GPQA) is unverified.

License

Gemma Terms of Use (Gemma4-E4B weights blended in) + Apache 2.0 (Qwen3-4B). Built on Qwen/Qwen3-4B and google/gemma-4-E4B.

Downloads last month: 3

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for FINAL-Bench/Darwin-V9-Chimera-4B-SFT

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

(1018)

this model

Quantizations

2 models