Instructions to use razor5050/codex-qwen2-5-0-5b-unsloth-codex1m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use razor5050/codex-qwen2-5-0-5b-unsloth-codex1m with Transformers:

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

pipe = pipeline("text-generation", model="razor5050/codex-qwen2-5-0-5b-unsloth-codex1m")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("razor5050/codex-qwen2-5-0-5b-unsloth-codex1m", device_map="auto")

PEFT
How to use razor5050/codex-qwen2-5-0-5b-unsloth-codex1m with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use razor5050/codex-qwen2-5-0-5b-unsloth-codex1m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "razor5050/codex-qwen2-5-0-5b-unsloth-codex1m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "razor5050/codex-qwen2-5-0-5b-unsloth-codex1m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/razor5050/codex-qwen2-5-0-5b-unsloth-codex1m

SGLang

How to use razor5050/codex-qwen2-5-0-5b-unsloth-codex1m 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 "razor5050/codex-qwen2-5-0-5b-unsloth-codex1m" \
    --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": "razor5050/codex-qwen2-5-0-5b-unsloth-codex1m",
		"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 "razor5050/codex-qwen2-5-0-5b-unsloth-codex1m" \
        --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": "razor5050/codex-qwen2-5-0-5b-unsloth-codex1m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use razor5050/codex-qwen2-5-0-5b-unsloth-codex1m with Docker Model Runner:
```
docker model run hf.co/razor5050/codex-qwen2-5-0-5b-unsloth-codex1m
```

codex-qwen2-5-0-5b-unsloth-codex1m / README.md

razor5050

Add initial model card

8f14b0e verified 4 months ago

preview code

Raw

History Blame

2.98 kB

	---
	license: apache-2.0
	base_model: Qwen/Qwen2.5-0.5B-Instruct
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- unsloth
	- qwen2
	- qwen2.5
	- lora
	- sft
	- code
	- reasoning
	- codex
	- peft
	- trl
	datasets:
	- Modotte/CodeX-2M-Thinking
	language:
	- en
	---

	# CodeX Qwen2.5 0.5B Unsloth SFT - 1M Rows

	This repository is prepared for a cloud-only Unsloth LoRA supervised fine-tuning run of `Qwen/Qwen2.5-0.5B-Instruct` on the first 1,000,000 rows of `Modotte/CodeX-2M-Thinking`.

	> Status: training setup/provisioning. Final metrics, checkpoints, adapters, inference samples, and report will be uploaded here during/after training.

	## Base Model

	- Base: [`Qwen/Qwen2.5-0.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
	- Architecture: `Qwen2ForCausalLM`
	- Parameters: ~494M
	- Context length: 32,768 tokens
	- License: Apache-2.0

	## Dataset

	- Dataset: [`Modotte/CodeX-2M-Thinking`](https://huggingface.co/datasets/Modotte/CodeX-2M-Thinking)
	- Planned subset: first 1,000,000 rows
	- Columns used:
	- `input` → user/problem prompt
	- `output` → assistant solution/reasoning/code response
	- Intended task: coding instruction following, algorithmic reasoning, solution explanation, and code generation.

	## Planned Training Method

	- Framework: Unsloth + TRL SFTTrainer + PEFT LoRA
	- Quantized base loading: 4-bit
	- LoRA rank: 32
	- LoRA alpha: 64
	- LoRA dropout: 0
	- Target modules:
	- `q_proj`, `k_proj`, `v_proj`, `o_proj`
	- `gate_proj`, `up_proj`, `down_proj`
	- Max sequence length for first run: 8,192 tokens
	- Epochs: 1
	- Checkpointing: approximately every 2 hours
	- Durable storage: Hugging Face Hub checkpoints and metrics

	## Planned Artifacts

	During training, this repo will receive:

	- `checkpoints/checkpoint-*` — resumable trainer checkpoints
	- `metrics/metrics.jsonl` — train/eval logs
	- `metrics/status.json` — latest job status
	- `final_lora_adapter/` — final PEFT LoRA adapter
	- `final_merged_16bit/` — merged model if cloud disk/runtime allows
	- `reports/inference_samples.json` — post-training inference outputs
	- `reports/TRAINING_REPORT.md` — final training report

	## Intended Use

	This model is intended for experimentation with small code-reasoning SFT models, especially:

	- Python coding assistance
	- algorithm explanation
	- competitive-programming style solution drafting
	- reasoning-heavy coding responses

	## Limitations

	- This is a sub-500M parameter model, so it should not be expected to match larger coding models.
	- The dataset is synthetic and may transfer dataset-specific response style.
	- Long outputs may still be limited by the training sequence length and generation settings.
	- The model may produce incorrect code; generated solutions require testing and review.

	## Safety and Evaluation

	Post-training evaluation will include sample inference prompts and loss tracking. This repository should not be treated as production-ready until final metrics and qualitative outputs are reviewed.