Instructions to use modrill/code-think-q4b-20260908 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modrill/code-think-q4b-20260908 with Transformers:

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

pipe = pipeline("text-generation", model="modrill/code-think-q4b-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-think-q4b-20260908")
model = AutoModelForCausalLM.from_pretrained("modrill/code-think-q4b-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-think-q4b-20260908 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modrill/code-think-q4b-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-think-q4b-20260908",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modrill/code-think-q4b-20260908

SGLang

How to use modrill/code-think-q4b-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-think-q4b-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-think-q4b-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-think-q4b-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-think-q4b-20260908",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use modrill/code-think-q4b-20260908 with Docker Model Runner:
```
docker model run hf.co/modrill/code-think-q4b-20260908
```

code-think-q4b-20260908 / README.md

modrill

Date unify to 20260908; formerly code-think-q4b-20260909

6a026be verified about 1 month ago

preview code

Raw History Blame Contribute Delete

5.65 kB

---
license: apache-2.0
base_model: Qwen/Qwen3-4B-Base
tags:
- code
- reasoning
- lora-merged
- livecodebench
pipeline_tag: text-generation
library_name: transformers
---
# code-think-q4b-20260908

Research checkpoint: **Qwen/Qwen3-4B-Base** (`906bfd4b4dc7f14ee4320094d8b41684abff8539`) after V4 LoRA SFT on a **Mix Distillation** payload, then merged to full weights.

This is a **research checkpoint, not a product**. Single-seed diagnostic numbers only. Do not treat DEV256 as a leaderboard claim.

License: **Apache-2.0**, inherited from [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) (verified from the local base `README.md` / `LICENSE`).

## Base, teacher, and data

| | |
|---|---|
| Student | `Qwen/Qwen3-4B-Base` revision `906bfd4b4dc7f14ee4320094d8b41684abff8539` |
| Recipe | Mix Distillation **Mix-Large** (Li et al., 2025, ["Small Models Struggle to Learn from Strong Reasoners"](https://arxiv.org/abs/2502.12143), arXiv:2502.12143): **0.2** traces from `Qwen/Qwen3-30B-A3B-Thinking-2507` : **0.8** traces from `Qwen/Qwen3-4B-Thinking-2507`, one teacher trace per problem |
| Problems | **4155** unique problems (`source_1ep_rows`); physical 2-epoch concat = **8310** rows |
| Mix split | **831** (30B) : **3324** (4B) rows in the 1-epoch mix (`n30`/`n4`) |
| Dose | **32,424,225** assistant tokens / epoch; endpoint **64,848,450** assistant tokens (2 epochs) |
| Train seed | **42** |

## Recipe

- LoRA **r64 / α128**, dropout 0.0, seven projections: `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`
- Embeddings / `lm_head` frozen except **two-sided trainable B-rows** for special tokens **151643** (`<|endoftext|>`), **151667** (`<think>`), **151668** (`</think>`). Qwen3-4B-Base embeddings were tied; training **untied** them. Token ids from `adapter/TOKEN_ROWS_META.json`.
- Assistant supervised tail: `<|endoftext|>` (**151643**)
- LR **1e-4**, AdamW (β 0.9/0.95), **cosine** over assistant-token dose, **warmup 6%** (3,890,907 / 64,848,450 tokens), weight decay **0.1** (LoRA; row WD 0)
- **bf16** activations, fp32 trainable masters, no packing, no truncation, context 32768
- **2 epochs**, physical concat of the 1-epoch mix (same order). Endpoint-only score; no checkpoint picking.

Merged weights in this repo are the 2-epoch endpoint (`step-000920`, 64,848,450 assistant tokens). The LoRA adapter and B-row file are under `adapter/`.

## Evaluation (DEV256)

256-problem LiveCodeBench-derived **dev** split. Seed **3407**, **think** mode, **no `<think>` prefill**, max generation ~32k (model context 32768), sandbox-verified **pass@1**. Temperature 0.6, top-p 0.95, top-k 20.

**Cap** = generations that hit the 32k length limit without closing `</think>`.

| Model | pass@1 | Cap | Notes |
|---|---:|---:|---|
| **code-think-q4b-20260908** | **73/256** | **136** | this repo; seed 3407 |
| Qwen3-4B-Base (same contract, think) | 63/256 | 6 | bare base, seed 3407 |
| Qwen3-4B-Base 5-seed band | 55.2 ± 4.9 | — | seeds {3407→61, 12345→52, 20260903→49, 777→55, 2024→59}; sample SD 4.92 |

Single seed. These are research checkpoints, not product scores.

### Why Mix (sibling V4 controls)

Pure strong-teacher traces **hurt** this 4B student; a same-size teacher and the 0.2:0.8 mix did not:

| Sibling (same student / recipe family) | pass@1 | Cap |
|---|---:|---:|
| V4 Q4B-THINK (100% 30B-A3B-Thinking traces) | 60/256 | 150 |
| V4 Q4B-THINK-T4BDATA (100% 4B-Thinking traces) | 72/256 | 106 |
| **This Mix 0.2 : 0.8** | **73/256** | **136** |

That pattern matches Li et al. 2025 (arXiv:2502.12143): small students often learn worse from much stronger reasoners than from a mixed or same-size teacher.

## Usage

Merged full weights; no PEFT required at inference. Think mode: pass `enable_thinking=True` and **do not** prefill `<think>`.

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "modrill/code-think-q4b-20260908"
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="bfloat16", device_map="auto"
)
system = (
    "You are an expert Python programmer. You will be given a question "
    "(problem specification) and will generate a correct Python program that "
    "matches the specification and passes all tests. You will NOT return "
    "anything except for the program."
)
messages = [
    {"role": "system", "content": system},
    {"role": "user", "content": problem_statement},
]
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True,  # think mode; no <think> prefill
)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
output = model.generate(
    **inputs,
    max_new_tokens=32768,
    do_sample=True,
    temperature=0.6,
    top_p=0.95,
    top_k=20,
)
print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False))
```

Stop ids used in the official eval: `151643` (`<|endoftext|>`), `151645` (`<|im_end|>`).

## Repo layout

- Root: merged HF weights (`config.json`, `model.safetensors`, tokenizer, `generation_config.json`, `chat_template.jinja`) plus the merge record `OFFICIAL_MERGE_RECEIPT.json`
- `adapter/`: LoRA (`adapter_config.json`, `adapter_model.safetensors`), two-sided B-rows (`token_rows_both_sides.safetensors`), `TOKEN_ROWS_META.json`, checkpoint `MANIFEST.json`
- `provenance/`: train `RUN_IDENTITY.json`, `TRAINING_CONFIG.json`, `POLICY.json`; DEV256 `COMPLETE.json`; mix builder and MQ0 near-dup report
- `MANIFEST.sha256`: sha256 of every uploaded file

Optimizer / resume states are **not** included.

	---
	license: apache-2.0
	base_model: Qwen/Qwen3-4B-Base
	tags:
	- code
	- reasoning
	- lora-merged
	- livecodebench
	pipeline_tag: text-generation
	library_name: transformers
	---

	# code-think-q4b-20260908

	Research checkpoint: Qwen/Qwen3-4B-Base (`906bfd4b4dc7f14ee4320094d8b41684abff8539`) after V4 LoRA SFT on a Mix Distillation payload, then merged to full weights.

	This is a research checkpoint, not a product. Single-seed diagnostic numbers only. Do not treat DEV256 as a leaderboard claim.

	License: Apache-2.0, inherited from [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) (verified from the local base `README.md` / `LICENSE`).

	## Base, teacher, and data

	\| \| \|
	\|---\|---\|
	\| Student \| `Qwen/Qwen3-4B-Base` revision `906bfd4b4dc7f14ee4320094d8b41684abff8539` \|
	\| Recipe \| Mix Distillation Mix-Large (Li et al., 2025, ["Small Models Struggle to Learn from Strong Reasoners"](https://arxiv.org/abs/2502.12143), arXiv:2502.12143): 0.2 traces from `Qwen/Qwen3-30B-A3B-Thinking-2507` : 0.8 traces from `Qwen/Qwen3-4B-Thinking-2507`, one teacher trace per problem \|
	\| Problems \| 4155 unique problems (`source_1ep_rows`); physical 2-epoch concat = 8310 rows \|
	\| Mix split \| 831 (30B) : 3324 (4B) rows in the 1-epoch mix (`n30`/`n4`) \|
	\| Dose \| 32,424,225 assistant tokens / epoch; endpoint 64,848,450 assistant tokens (2 epochs) \|
	\| Train seed \| 42 \|

	## Recipe

	- LoRA r64 / α128, dropout 0.0, seven projections: `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`
	- Embeddings / `lm_head` frozen except two-sided trainable B-rows for special tokens 151643 (`<\|endoftext\|>`), 151667 (`<think>`), 151668 (`</think>`). Qwen3-4B-Base embeddings were tied; training untied them. Token ids from `adapter/TOKEN_ROWS_META.json`.
	- Assistant supervised tail: `<\|endoftext\|>` (151643)
	- LR 1e-4, AdamW (β 0.9/0.95), cosine over assistant-token dose, warmup 6% (3,890,907 / 64,848,450 tokens), weight decay 0.1 (LoRA; row WD 0)
	- bf16 activations, fp32 trainable masters, no packing, no truncation, context 32768
	- 2 epochs, physical concat of the 1-epoch mix (same order). Endpoint-only score; no checkpoint picking.

	Merged weights in this repo are the 2-epoch endpoint (`step-000920`, 64,848,450 assistant tokens). The LoRA adapter and B-row file are under `adapter/`.

	## Evaluation (DEV256)

	256-problem LiveCodeBench-derived dev split. Seed 3407, think mode, no `<think>` prefill, max generation ~32k (model context 32768), sandbox-verified pass@1. Temperature 0.6, top-p 0.95, top-k 20.

	Cap = generations that hit the 32k length limit without closing `</think>`.

	\| Model \| pass@1 \| Cap \| Notes \|
	\|---\|---:\|---:\|---\|
	\| code-think-q4b-20260908 \| 73/256 \| 136 \| this repo; seed 3407 \|
	\| Qwen3-4B-Base (same contract, think) \| 63/256 \| 6 \| bare base, seed 3407 \|
	\| Qwen3-4B-Base 5-seed band \| 55.2 ± 4.9 \| — \| seeds {3407→61, 12345→52, 20260903→49, 777→55, 2024→59}; sample SD 4.92 \|

	Single seed. These are research checkpoints, not product scores.

	### Why Mix (sibling V4 controls)

	Pure strong-teacher traces hurt this 4B student; a same-size teacher and the 0.2:0.8 mix did not:

	\| Sibling (same student / recipe family) \| pass@1 \| Cap \|
	\|---\|---:\|---:\|
	\| V4 Q4B-THINK (100% 30B-A3B-Thinking traces) \| 60/256 \| 150 \|
	\| V4 Q4B-THINK-T4BDATA (100% 4B-Thinking traces) \| 72/256 \| 106 \|
	\| This Mix 0.2 : 0.8 \| 73/256 \| 136 \|

	That pattern matches Li et al. 2025 (arXiv:2502.12143): small students often learn worse from much stronger reasoners than from a mixed or same-size teacher.

	## Usage

	Merged full weights; no PEFT required at inference. Think mode: pass `enable_thinking=True` and do not prefill `<think>`.

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	repo = "modrill/code-think-q4b-20260908"
	tokenizer = AutoTokenizer.from_pretrained(repo)
	model = AutoModelForCausalLM.from_pretrained(
	repo, torch_dtype="bfloat16", device_map="auto"
	)

	system = (
	"You are an expert Python programmer. You will be given a question "
	"(problem specification) and will generate a correct Python program that "
	"matches the specification and passes all tests. You will NOT return "
	"anything except for the program."
	)
	messages = [
	{"role": "system", "content": system},
	{"role": "user", "content": problem_statement},
	]
	prompt = tokenizer.apply_chat_template(
	messages,
	tokenize=False,
	add_generation_prompt=True,
	enable_thinking=True, # think mode; no <think> prefill
	)
	inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
	output = model.generate(
	**inputs,
	max_new_tokens=32768,
	do_sample=True,
	temperature=0.6,
	top_p=0.95,
	top_k=20,
	)
	print(tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False))
	```

	Stop ids used in the official eval: `151643` (`<\|endoftext\|>`), `151645` (`<\|im_end\|>`).

	## Repo layout

	- Root: merged HF weights (`config.json`, `model.safetensors`, tokenizer, `generation_config.json`, `chat_template.jinja`) plus the merge record `OFFICIAL_MERGE_RECEIPT.json`
	- `adapter/`: LoRA (`adapter_config.json`, `adapter_model.safetensors`), two-sided B-rows (`token_rows_both_sides.safetensors`), `TOKEN_ROWS_META.json`, checkpoint `MANIFEST.json`
	- `provenance/`: train `RUN_IDENTITY.json`, `TRAINING_CONFIG.json`, `POLICY.json`; DEV256 `COMPLETE.json`; mix builder and MQ0 near-dup report
	- `MANIFEST.sha256`: sha256 of every uploaded file

	Optimizer / resume states are not included.