Instructions to use pankajmathur/RenCoder-Devstral-Small-2507 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pankajmathur/RenCoder-Devstral-Small-2507 with Transformers:

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

pipe = pipeline("text-generation", model="pankajmathur/RenCoder-Devstral-Small-2507")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pankajmathur/RenCoder-Devstral-Small-2507")
model = AutoModelForCausalLM.from_pretrained("pankajmathur/RenCoder-Devstral-Small-2507", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pankajmathur/RenCoder-Devstral-Small-2507 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pankajmathur/RenCoder-Devstral-Small-2507"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pankajmathur/RenCoder-Devstral-Small-2507",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pankajmathur/RenCoder-Devstral-Small-2507

SGLang

How to use pankajmathur/RenCoder-Devstral-Small-2507 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 "pankajmathur/RenCoder-Devstral-Small-2507" \
    --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": "pankajmathur/RenCoder-Devstral-Small-2507",
		"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 "pankajmathur/RenCoder-Devstral-Small-2507" \
        --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": "pankajmathur/RenCoder-Devstral-Small-2507",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pankajmathur/RenCoder-Devstral-Small-2507 with Docker Model Runner:
```
docker model run hf.co/pankajmathur/RenCoder-Devstral-Small-2507
```

pankajmathur commited on Mar 27

Commit

0f20988

verified ·

1 Parent(s): 707442a

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -3

README.md CHANGED Viewed

@@ -3,9 +3,11 @@ license: apache-2.0
 base_model:
 - mistralai/Devstral-Small-2507
 tags:
-- mistral
 - code
 - sft
 language:
 - en
 library_name: transformers
@@ -16,7 +18,7 @@ datasets:
 # RenCoder-Devstral-Small-2507
-This model is a fine tuned version of [mistralai/Devstral-Small-2507](https://huggingface.co/mistralai/Devstral-Small-2507) on muliple agentic coding datasets.
 <img src="https://huggingface.co/pankajmathur/RenCoder-Ministral-8B-Instruct-2410/resolve/main/RenCoder.png" height="600" width="600" />
@@ -42,4 +44,4 @@ This model inherits the Apache 2.0 license from the base Devstral-Small-2507 mod
 ## Acknowledgements
 - [Mistral AI](https://mistral.ai/) for the Devstral-Small-2507 base model
-- [Axolotl](https://github.com/axolotl-ai-cloud/axolotl) for training infrastructure

 base_model:
 - mistralai/Devstral-Small-2507
 tags:
 - code
 - sft
+- rl
+- rlvr
+- grpo
 language:
 - en
 library_name: transformers
 # RenCoder-Devstral-Small-2507
+This model is a SFT + RLVR (DPO+GRPO) version of [mistralai/Devstral-Small-2507](https://huggingface.co/mistralai/Devstral-Small-2507) on muliple agentic coding datasets (SWE-Bench, etc).
 <img src="https://huggingface.co/pankajmathur/RenCoder-Ministral-8B-Instruct-2410/resolve/main/RenCoder.png" height="600" width="600" />
 ## Acknowledgements
 - [Mistral AI](https://mistral.ai/) for the Devstral-Small-2507 base model
+- [Axolotl](https://github.com/axolotl-ai-cloud/axolotl) and [NVIDIA-NeMo Gym](https://github.com/NVIDIA-NeMo/Gym) for training infrastructure