Instructions to use modrill/Qwen3-4B-Base-ThinkCode-A-NH025 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modrill/Qwen3-4B-Base-ThinkCode-A-NH025 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Base")
model = PeftModel.from_pretrained(base_model, "modrill/Qwen3-4B-Base-ThinkCode-A-NH025")

Transformers

How to use modrill/Qwen3-4B-Base-ThinkCode-A-NH025 with Transformers:

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

pipe = pipeline("text-generation", model="modrill/Qwen3-4B-Base-ThinkCode-A-NH025")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("modrill/Qwen3-4B-Base-ThinkCode-A-NH025", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use modrill/Qwen3-4B-Base-ThinkCode-A-NH025 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modrill/Qwen3-4B-Base-ThinkCode-A-NH025"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modrill/Qwen3-4B-Base-ThinkCode-A-NH025",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/modrill/Qwen3-4B-Base-ThinkCode-A-NH025

SGLang

How to use modrill/Qwen3-4B-Base-ThinkCode-A-NH025 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/Qwen3-4B-Base-ThinkCode-A-NH025" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modrill/Qwen3-4B-Base-ThinkCode-A-NH025",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/Qwen3-4B-Base-ThinkCode-A-NH025" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modrill/Qwen3-4B-Base-ThinkCode-A-NH025",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use modrill/Qwen3-4B-Base-ThinkCode-A-NH025 with Docker Model Runner:
```
docker model run hf.co/modrill/Qwen3-4B-Base-ThinkCode-A-NH025
```

Qwen3-4B-Base-ThinkCode-A-NH025 / README.md

modrill

Add files using upload-large-folder tool

aedefab verified 6 days ago

preview code

Raw

History Blame Contribute Delete

4.99 kB

metadata

license: apache-2.0
library_name: peft
pipeline_tag: text-generation
base_model: Qwen/Qwen3-4B-Base
base_model_relation: adapter
tags:
  - peft
  - lora
  - transformers
  - safetensors
  - qwen3
  - code
  - text-generation
model-index:
  - name: Qwen3-4B-Base-ThinkCode-A-NH025 PEFT Adapter
    results:
      - task:
          type: text-generation
          name: Code Generation
        dataset:
          name: EvalScope Full1055 corrected (development-only)
          type: evalscope-full1055-corrected-development
        metrics:
          - type: pass@1
            name: resolved aggregate code_only pass@1 (3 seeds)
            value: 25.09

Qwen3-4B-Base-ThinkCode-A-NH025 — PEFT Adapter

This repository contains a PEFT LoRA adapter only. It does not contain the Qwen3 base-model weights and cannot be loaded as a standalone causal language model.

The required base is Qwen/Qwen3-4B-Base at the fixed revision 906bfd4b4dc7f14ee4320094d8b41684abff8539.

Adapter construction

A-NH025 is the Phase A no-head arm. Starting from the completed source LoRA, every selected transformer-body LoRA B tensor is multiplied by 0.25 in FP32, while the lm_head LoRA B tensor is multiplied by 0, making its effective head/shared-embedding delta exactly zero. LoRA A tensors are unchanged. With lora_alpha=128 and r=64, PEFT applies the intended body delta without a language-model-head delta across the 253 declared modules.

The effective-zero lm_head adapter is omitted from the release state and target list; this is exactly equivalent to its validated zero delta and avoids packaging any base-layer tensor. MODULE_SCALE_MANIFEST.json retains the explicit zero-head contract and records every logical module, source tensor key, physical base weight, and scale. This release is from the completed Phase A delta-scaling line; it is not the later failed NEXTGEN route and does not include subsequent protocol-repair experiments.

Loading with PEFT

Use recent transformers and peft versions. Load the fixed base first, then attach this adapter:

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_id = "Qwen/Qwen3-4B-Base"
base_revision = "906bfd4b4dc7f14ee4320094d8b41684abff8539"
adapter_id = "modrill/Qwen3-4B-Base-ThinkCode-A-NH025"

tokenizer = AutoTokenizer.from_pretrained(base_id, revision=base_revision)
base = AutoModelForCausalLM.from_pretrained(
    base_id,
    revision=base_revision,
    torch_dtype="auto",
    device_map="auto",
)
model = PeftModel.from_pretrained(base, adapter_id)

messages = [{"role": "user", "content": "Write a Python function that checks whether a number is prime."}]
prompt = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=False,
)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
eos_ids = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|im_end|>"),
]
outputs = model.generate(**inputs, max_new_tokens=2048, eos_token_id=eos_ids)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True))

The base tokenizer's chat template supports enable_thinking. Disable it for direct code generation matching the concise screening style, or enable it when explicit reasoning is desired. Pass both <|endoftext|> and <|im_end|> as EOS IDs. Keep the combined prompt and generated sequence within 32K tokens, the fixed base model configuration limit, unless a separate long-context extension is validated.

Development evaluation

Across three preregistered seeds on the corrected EvalScope Full1055 development suite, the resolved code_only aggregate was 794/3165 = 25.09%. Relative to the fixed BASE, the estimated change was approximately +0.98 percentage points, with an approximate 95% confidence interval of [+0.095, +1.833] percentage points. The Holm-adjusted p-value was 0.489.

These results are development-only, not a held-out formal claim. In the original bidirectional scoring for seed=3407, some outcomes flipped between PASS and TLE because of the execution environment. Those cases were resolved by fixed single-CPU serial rejudgment, which does not eliminate all scorer, timing, or environment uncertainty.

Limitations

This adapter requires the exact base model and should not be loaded alone.
The evidence is development-only and includes scorer-environment uncertainty.
Generated code can be incorrect, insecure, or non-compiling; sandbox and test it independently.
No production safety, security, or suitability certification is implied.

License

The fixed base card and included license identify Apache-2.0. This adapter preserves that license text and metadata. Users should independently verify the upstream Qwen3 license, notices, training-data terms, and applicability to their use case.