Instructions to use modrill/code-nothink-q8b-20260908 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modrill/code-nothink-q8b-20260908 with Transformers:

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

pipe = pipeline("text-generation", model="modrill/code-nothink-q8b-20260908")
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("modrill/code-nothink-q8b-20260908")
model = AutoModelForCausalLM.from_pretrained("modrill/code-nothink-q8b-20260908", 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 modrill/code-nothink-q8b-20260908 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modrill/code-nothink-q8b-20260908"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modrill/code-nothink-q8b-20260908",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modrill/code-nothink-q8b-20260908

SGLang

How to use modrill/code-nothink-q8b-20260908 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 "modrill/code-nothink-q8b-20260908" \
    --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": "modrill/code-nothink-q8b-20260908",
		"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 "modrill/code-nothink-q8b-20260908" \
        --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": "modrill/code-nothink-q8b-20260908",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use modrill/code-nothink-q8b-20260908 with Docker Model Runner:
```
docker model run hf.co/modrill/code-nothink-q8b-20260908
```

code-nothink-q8b-20260908 / README.md

modrill

Rename card to code-nothink-q8b-20260908; formerly Qwen3-8B-Base-code-v4-nothink

631233c verified about 2 months ago

preview code

Raw History Blame Contribute Delete

3.39 kB

---
license: apache-2.0
base_model: Qwen/Qwen3-8B-Base
tags:
- code
- livecodebench
- sft
- lora-merged
- nothink
library_name: transformers
---
# code-nothink-q8b-20260908

Formerly `Qwen3-8B-Base-code-v4-nothink` (HF redirect).

**Arm ID:** `Q8B-NOTHINK`  
**Run ID:** `t30b2507-q8b-nothink-v4-tail151643`

Merged full bf16 weights used for the official DEV256 NoThink evaluation. Tokenizer files in this repo are the **eval-caliber** bundle (`qwen3-v4-tail151643`); they overlay any tokenizer files that were present in the merge directory (the merge tree's `tokenizer.json` was a different, larger file).

**Exploratory result (2 eval seeds), not a preregistered confirmatory claim.**

## Base model

- Hugging Face: [`Qwen/Qwen3-8B-Base`](https://huggingface.co/Qwen/Qwen3-8B-Base)
- Revision: `49e3418fbbbca6ecbdf9608b4d22e5a407081db4`

## Training

- Method: LoRA r64 / α128 on seven projections (`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`), then merged into full-model bf16 safetensors
- Data: NoThink code SFT (paired V4, physical 2-epoch concat)
- Endpoint (score): **step 142**, **9,455,736** assistant tokens — endpoint-as-score, no checkpoint picking
- Train seed 42; LR `1e-4`; context 8192; AdamW; cosine by assistant-token dose
- Host: local GPU 3 (retrain after mathbox3 host loss); eval tokenizer renderer `qwen3-v4-tail151643`

## Evaluation

- Suite: official LiveCodeBench **DEV256**
- Mode **NoThink**, `max_model_len` **8192**, vLLM **0.28.0**; do not prefill `<think>`
- Metric: sandbox pass@1 = passed / 256
- Seed 12345 used the same merged weights, tokenizer, and vLLM command as seed 3407 except `--seed` and the serve port. Results: `/workspace/code-sft-runs/rstar-eval/official-dev256-seeds/seed12345/`

| seed | arm | arm cap | Base | Base cap | McNemar arm_only / base_only | p |
|---|---|---|---|---|---|---|
| 3407 | 70/256 (27.3%) | 78 | 59/256 (23.0%) | 21 | 25 / 14 | 0.108 |
| 12345 | 84/256 (32.8%) | 75 | 57/256 (22.3%) | 23 | 37 / 10 | 9.8e-05 |
| pooled 512 | — | — | — | — | 62 / 24 | 5.1e-05 |

Mean: arm **77.0 (30.1%)** vs Base **58.0 (22.7%)**, Δ ≈ **+19**.

Arm pass@1 moves a lot across seeds (70 vs 84); Base is stable (57–59). The two-seed pooled paired difference is significant (**p = 5.1e-05**). Still exploratory (2 seeds, not preregistered).

## Provenance note

The same identity (seed 42, 9,455,736 assistant tokens, lr 1e-4, LoRA r64/α128) was previously trained once on another machine and scored 76/256 vs Base 57/256 (McNemar p=0.0019). That host went down and the weights plus eval cache were lost. This repository is the local GPU 3 retrain. The two-run difference (arm −6, Base +2) is single-seed cross-machine noise. This result is a single-seed exploratory outcome, not a confirmatory claim.

## Inference notes

- Use **this repository's** tokenizer and `chat_template.jinja`.
- NoThink: do not prefill `<think>`; if the template accepts `enable_thinking`, keep it false.
- Stop token ids: **151643** (`<|endoftext|>`) and **151645** (`<|im_end|>`).
- Eval sampling used temperature 0.7, top_p 0.8, top_k 20.

## Weight checksum

- `model.safetensors` (16,381,517,208 bytes): `sha256:fdde336f8a504ce0dae4537b0955bbe660e1072ec093e43cce548e5654958a94`

`OFFICIAL_MERGE_RECEIPT.json` is included for merge provenance. LoRA adapter checkpoints are **not** in this repo.

	---
	license: apache-2.0
	base_model: Qwen/Qwen3-8B-Base
	tags:
	- code
	- livecodebench
	- sft
	- lora-merged
	- nothink
	library_name: transformers
	---

	# code-nothink-q8b-20260908

	Formerly `Qwen3-8B-Base-code-v4-nothink` (HF redirect).

	Arm ID: `Q8B-NOTHINK`
	Run ID: `t30b2507-q8b-nothink-v4-tail151643`

	Merged full bf16 weights used for the official DEV256 NoThink evaluation. Tokenizer files in this repo are the eval-caliber bundle (`qwen3-v4-tail151643`); they overlay any tokenizer files that were present in the merge directory (the merge tree's `tokenizer.json` was a different, larger file).

	Exploratory result (2 eval seeds), not a preregistered confirmatory claim.

	## Base model

	- Hugging Face: [`Qwen/Qwen3-8B-Base`](https://huggingface.co/Qwen/Qwen3-8B-Base)
	- Revision: `49e3418fbbbca6ecbdf9608b4d22e5a407081db4`

	## Training

	- Method: LoRA r64 / α128 on seven projections (`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`), then merged into full-model bf16 safetensors
	- Data: NoThink code SFT (paired V4, physical 2-epoch concat)
	- Endpoint (score): step 142, 9,455,736 assistant tokens — endpoint-as-score, no checkpoint picking
	- Train seed 42; LR `1e-4`; context 8192; AdamW; cosine by assistant-token dose
	- Host: local GPU 3 (retrain after mathbox3 host loss); eval tokenizer renderer `qwen3-v4-tail151643`

	## Evaluation

	- Suite: official LiveCodeBench DEV256
	- Mode NoThink, `max_model_len` 8192, vLLM 0.28.0; do not prefill `<think>`
	- Metric: sandbox pass@1 = passed / 256
	- Seed 12345 used the same merged weights, tokenizer, and vLLM command as seed 3407 except `--seed` and the serve port. Results: `/workspace/code-sft-runs/rstar-eval/official-dev256-seeds/seed12345/`

	\| seed \| arm \| arm cap \| Base \| Base cap \| McNemar arm_only / base_only \| p \|
	\|---\|---\|---\|---\|---\|---\|---\|
	\| 3407 \| 70/256 (27.3%) \| 78 \| 59/256 (23.0%) \| 21 \| 25 / 14 \| 0.108 \|
	\| 12345 \| 84/256 (32.8%) \| 75 \| 57/256 (22.3%) \| 23 \| 37 / 10 \| 9.8e-05 \|
	\| pooled 512 \| — \| — \| — \| — \| 62 / 24 \| 5.1e-05 \|

	Mean: arm 77.0 (30.1%) vs Base 58.0 (22.7%), Δ ≈ +19.

	Arm pass@1 moves a lot across seeds (70 vs 84); Base is stable (57–59). The two-seed pooled paired difference is significant (p = 5.1e-05). Still exploratory (2 seeds, not preregistered).

	## Provenance note

	The same identity (seed 42, 9,455,736 assistant tokens, lr 1e-4, LoRA r64/α128) was previously trained once on another machine and scored 76/256 vs Base 57/256 (McNemar p=0.0019). That host went down and the weights plus eval cache were lost. This repository is the local GPU 3 retrain. The two-run difference (arm −6, Base +2) is single-seed cross-machine noise. This result is a single-seed exploratory outcome, not a confirmatory claim.

	## Inference notes

	- Use this repository's tokenizer and `chat_template.jinja`.
	- NoThink: do not prefill `<think>`; if the template accepts `enable_thinking`, keep it false.
	- Stop token ids: 151643 (`<\|endoftext\|>`) and 151645 (`<\|im_end\|>`).
	- Eval sampling used temperature 0.7, top_p 0.8, top_k 20.

	## Weight checksum

	- `model.safetensors` (16,381,517,208 bytes): `sha256:fdde336f8a504ce0dae4537b0955bbe660e1072ec093e43cce548e5654958a94`

	`OFFICIAL_MERGE_RECEIPT.json` is included for merge provenance. LoRA adapter checkpoints are not in this repo.