Instructions to use 0XARTEX/artex-coder-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0XARTEX/artex-coder-7b with Transformers:

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

pipe = pipeline("text-generation", model="0XARTEX/artex-coder-7b")
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("0XARTEX/artex-coder-7b")
model = AutoModelForCausalLM.from_pretrained("0XARTEX/artex-coder-7b", 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 0XARTEX/artex-coder-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0XARTEX/artex-coder-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0XARTEX/artex-coder-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0XARTEX/artex-coder-7b

SGLang

How to use 0XARTEX/artex-coder-7b 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 "0XARTEX/artex-coder-7b" \
    --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": "0XARTEX/artex-coder-7b",
		"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 "0XARTEX/artex-coder-7b" \
        --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": "0XARTEX/artex-coder-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0XARTEX/artex-coder-7b with Docker Model Runner:
```
docker model run hf.co/0XARTEX/artex-coder-7b
```

Artex Coder 7B

Artex is a concise, accurate, to-the-point coding assistant, fine-tuned from Qwen2.5-Coder-7B-Instruct. It answers in the user's language.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "0XARTEX/artex-coder-7b"
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto", device_map="auto")

messages = [{"role": "user", "content": "Write a Python function that checks if a string is a palindrome."}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
output = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(output[0][inputs.shape[1]:], skip_special_tokens=True))

Training


Base model	Qwen/Qwen2.5-Coder-7B-Instruct (bf16)
Method	LoRA (r=16, alpha=32, all linear layers), merged into the base weights
Data	4,000 samples from Magicoder-OSS-Instruct-75K (MIT) + Artex identity conversations (EN/ID)
Loss	completion-only (assistant replies)
Epochs	2, lr 1e-4 cosine, effective batch 16, max length 2048
Hardware	1× NVIDIA H100 80GB, ~18 minutes
Validation loss	0.286 → 0.172

Limitations

No standardized benchmark (HumanEval, MBPP) has been run yet; quality is expected to be close to the base model.
Like any LLM, Artex can produce incorrect or insecure code. Review its output before using it.

License

Apache 2.0, the same as the base model. The training data from Magicoder-OSS-Instruct-75K is MIT-licensed.

surplus-launcher: 0xab3fA342FEa0d30f99fEF14B3DdBa7bEc363729D

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for 0XARTEX/artex-coder-7b

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Finetuned

(472)

this model

0XARTEX
/

artex-coder-7b

Artex Coder 7B

Usage

Training

Limitations

License

Model tree for 0XARTEX/artex-coder-7b

Dataset used to train 0XARTEX/artex-coder-7b