Downloads · 30 days
21
24% of all-time downloads
Hemlock-Qwen3-Coder-REAP-25B-A3B
nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B
Hemlock-Qwen3-Coder-REAP-25B-A3B is a text generation model from nbeerbower. Use it when you need the model to write or continue text. It is set up for transformers.
All-time downloads
89
Public
Parameters
24.9B
49.7 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors49.7 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- qwen3_moe
- Access
- Public
- Created
- Dec 17, 2025
- Updated
- Dec 18, 2025
- SHA
- 8bf3c991
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Hemlock-Qwen3-Coder-REAP-25B-A3B
An attempt to train Qwen3-Coder on The Hemlock Programming Language using SFT.
Training Configuration
| Parameter | Value |
|---|---|
| Training Mode | SFT |
| Base Model | cerebras/Qwen3-Coder-REAP-25B-A3B |
| Learning Rate | 9e-05 |
| Epochs | 2 |
| Batch Size | 1 |
| Gradient Accumulation | 16 |
| Effective Batch Size | 16 |
| Max Sequence Length | 2048 |
| Optimizer | paged_adamw_8bit |
| LR Scheduler | cosine |
| Warmup Ratio | 0.05 |
| Weight Decay | 0.01 |
| Max Grad Norm | 0.2 |
| Seed | 42 |
| LoRA Rank (r) | 16 |
| LoRA Alpha | 8 |
| LoRA Dropout | 0.05 |
| Target Modules | up_proj, down_proj, gate_proj, k_proj, q_proj, v_proj, o_proj |
| Quantization | 4-bit (NF4) |
| GPU | NVIDIA RTX A6000 |
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_moe
- Created
- Dec 17, 2025
- Updated
- Dec 18, 2025