Instructions to use xemha125/RxCodexV1-MBN-medium-ctx256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xemha125/RxCodexV1-MBN-medium-ctx256 with Transformers:

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

pipe = pipeline("text-generation", model="xemha125/RxCodexV1-MBN-medium-ctx256")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xemha125/RxCodexV1-MBN-medium-ctx256")
model = AutoModelForCausalLM.from_pretrained("xemha125/RxCodexV1-MBN-medium-ctx256", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xemha125/RxCodexV1-MBN-medium-ctx256 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xemha125/RxCodexV1-MBN-medium-ctx256"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xemha125/RxCodexV1-MBN-medium-ctx256",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/xemha125/RxCodexV1-MBN-medium-ctx256

SGLang

How to use xemha125/RxCodexV1-MBN-medium-ctx256 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 "xemha125/RxCodexV1-MBN-medium-ctx256" \
    --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": "xemha125/RxCodexV1-MBN-medium-ctx256",
		"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 "xemha125/RxCodexV1-MBN-medium-ctx256" \
        --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": "xemha125/RxCodexV1-MBN-medium-ctx256",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use xemha125/RxCodexV1-MBN-medium-ctx256 with Docker Model Runner:
```
docker model run hf.co/xemha125/RxCodexV1-MBN-medium-ctx256
```

RxCodexV1-MBN-medium-ctx256

Commit History

Upload tokenizer

22df32f
verified

Rx MHA commited on May 8, 2025

Upload MBN baseline model (GPT-2 Medium size, n_ctx=256, trained 10000 steps)

f8897a4
verified

Rx MHA commited on May 8, 2025

initial commit

b710b99
verified

Rx MHA commited on May 8, 2025

Commit History

Upload tokenizer 22df32f verified

Upload MBN baseline model (GPT-2 Medium size, n_ctx=256, trained 10000 steps) f8897a4 verified

initial commit b710b99 verified

Upload tokenizer

22df32f
verified

Upload MBN baseline model (GPT-2 Medium size, n_ctx=256, trained 10000 steps)

f8897a4
verified

initial commit

b710b99
verified