Downloads · 30 days
27
2% of all-time downloads
criticleanGPT-Qwen3-8B-RL
neelshah123098/criticleanGPT-Qwen3-8B-RL
criticleanGPT-Qwen3-8B-RL is a text generation model from neelshah123098. Use it when you need the model to write or continue text. It is set up for llama.cpp. The card lists the license as other.
This repository packages a GGUF runtime for m-a-p/CriticLeanGPT-Qwen3-8B-RL with an OpenAI-compatible llama.cpp server and a FormalRx structured-diagnosis endpoint path.
All-time downloads
1.2K
Public
Repo size
5.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf5.1 GB · 84%
At a glance
- Task
- Text Generation
- Library
- llama.cpp
- License
- other
- Access
- Public
- Created
- Jun 14, 2026
- Updated
- Jun 25, 2026
- SHA
- 3333cd78
Try a prompt
Model card
From the Hugging Face model README
CriticLeanGPT-Qwen3-8B-RL FormalRx Runtime
This repository packages a GGUF runtime for m-a-p/CriticLeanGPT-Qwen3-8B-RL
with an OpenAI-compatible llama.cpp server and a FormalRx structured-diagnosis
endpoint path.
Files
model.gguf: Q4_K_M GGUF model artifact.bin/llama-server: bundled monolithic llama.cpp server binary for this package.run.sh: launcher used by the Docker image.Dockerfile: NVIDIA Docker image recipe for isolated deployment.docker-compose.yml: Compose service for the Docker deployment path.prompts/formalrx_prompt_template.txt: row prompt template used by the runner.prompts/formalrx_system_prompt.md: recommended system prompt for endpoint use.clients/formalrx_endpoint_runner.py: dataset-to-endpoint runner that writes predictions JSONL and an optional submission zip.examples/request_template.json: OpenAI-compatible request skeleton.
- Task
- Text Generation
- Library
- llama.cpp
- License
- other
- Created
- Jun 14, 2026
- Updated
- Jun 25, 2026