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 / metrics_under8000 /status.json

razor5050

Update under8000 status

acc2290 verified 4 months ago

Raw

History Blame

2.06 kB

	{
	"updated_at": "2026-05-10T03:37:26.704562+00:00",
	"phase": "checkpoint_saved",
	"dataset_dir": "/workspace/datasets/codex_qwen_chatml_under8000",
	"filter_meta": {
	"done": true,
	"streaming_jsonl": true,
	"model": "unsloth/Qwen2.5-0.5B-Instruct",
	"source_arrow": "/workspace/.cache/huggingface/datasets/Modotte___code_x-2_m-thinking/default/0.0.0/f9a4622fe9ccaa71509beea80e3bc69739cbbfa2/cache-050c121d84d2d7dc.arrow",
	"dataset_dir": "/workspace/datasets/codex_qwen_chatml_under8000",
	"train_jsonl": "/workspace/datasets/codex_qwen_chatml_under8000/train.jsonl",
	"eval_jsonl": "/workspace/datasets/codex_qwen_chatml_under8000/eval.jsonl",
	"method": "Qwen ChatML text filtered by strict len(tokens)<8000 using truncation=max_length=8000 classification; written as streaming JSONL to avoid RAM blow-up",
	"threshold": 8000,
	"all_selected_rows": 1000000,
	"below_8000_all_selected": 600235,
	"at_or_above_8000_all_selected": 399765,
	"train_source_rows_first_995k": 995000,
	"train_filtered_rows": 597222,
	"train_rejected_rows": 397778,
	"eval_source_rows_last_5k": 5000,
	"eval_filtered_rows": 3013,
	"eval_rejected_rows": 1987,
	"pct_below_all": 60.0235,
	"pct_below_train": 60.022312,
	"pct_below_eval": 60.26,
	"elapsed_sec": 2530.8,
	"completed_at": "2026-05-09T17:34:26Z"
	},
	"model": "unsloth/Qwen2.5-0.5B-Instruct",
	"rows": 600235,
	"train_rows": 597222,
	"eval_rows": 3013,
	"max_seq_length": 8192,
	"tokenization_verify": {
	"columns": [
	"input_ids",
	"attention_mask"
	],
	"checked_rows": 5000,
	"sample_min_input_len": 418,
	"sample_max_input_len": 7999
	},
	"run_name": "codex-qwen05b-under8000-unsloth-20260509-165210",
	"step": 12552,
	"epoch": 0.1681116904601639,
	"latest_logs": {
	"loss": 0.8758007049560547,
	"grad_norm": 0.9693902134895325,
	"learning_rate": 0.0001901640063777055,
	"epoch": 0.1681116904601639
	},
	"checkpoint": "/workspace/codex-qwen-under8000-lora-run/trainer_output/checkpoint-12552"
	}