Downloads · 30 days
15
17% of all-time downloads
portkit-coder-8b-grpo7
alexchapin/portkit-coder-8b-grpo7
portkit-coder-8b-grpo7 is a text generation model from alexchapin. Use it when you need the model to write or continue text. It is set up for transformers.
Self-reflection RL fine-tuned model for Minecraft Java (Forge) to Bedrock Add-on conversion.
All-time downloads
89
Public
Parameters
8.2B
20.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen3
- Access
- Public
- Created
- May 19, 2026
- Updated
- May 20, 2026
- SHA
- 3c521cd3
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
alexchapin/portkit-coder-8b-grpo7
Self-reflection RL fine-tuned model for Minecraft Java (Forge) to Bedrock Add-on conversion.
Model Details
- Base model: Qwen/Qwen3-8B
- Training method: GRPO with self-reflection rewards (inspired by ReflexiCoder)
- Checkpoint: GRPO7 final (100 steps, group_size=12)
- Learning rate: 1e-6
Reward Components
| Component | Weight | Description |
|---|---|---|
| manifest_completeness | 0.20 | format_version, header, uuid, version validation |
| structure_building | 0.20 | JSON structure, module types |
| api_correctness | 0.20 | @minecraft/server API usage |
| js_syntax | 0.20 | JavaScript syntax validity |
| self_reflection | 0.20 | Correction pattern detection |
Training Details
- Steps: 100
- Group size: 12
- Reward function: Self-reflection rewards inspired by ReflexiCoder
- Key insight: Lower LR (1e-6) for stability; slightly better JS API correctness (72.7% vs 72.5%)
Usage
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("alexchapin/portkit-coder-8b-grpo7")
Framework Versions
- tinker-cookbook: 0.4.1
- transformers: 5.5.3
- torch: 2.11.0+rocm7.2
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3
- Languages
- en
- Created
- May 19, 2026
- Updated
- May 20, 2026