|
Download README.md from VedMedTest/vetbot-v3: direct link, hf CLI and curl.
- Browser
- Download file 692 Bytes
-
https://huggingface.co/VedMedTest/vetbot-v3/resolve/main/README.md
- Command line
-
hf download hf://VedMedTest/vetbot-v3/README.md
-
curl -L -o README.md https://huggingface.co/VedMedTest/vetbot-v3/resolve/main/README.md
692 Bytes
| # VetBot V3 - Qwen2.5-72B LoRA Adapter | |
| Fine-tuned Qwen2.5-72B-Instruct for veterinary medicine Q&A. | |
| ## Training Summary | |
| | Parameter | Value | | |
| |-----------|-------| | |
| | Base Model | Qwen/Qwen2.5-72B-Instruct | | |
| | Method | LoRA (r=128, alpha=256) | | |
| | Trainable Params | 1.68B / 74.4B (2.26%) | | |
| | Hardware | 4x NVIDIA H200 (141GB each) | | |
| | Training Time | 8.46 hours | | |
| | Epochs | 3 | | |
| | Train Samples | 41,506 | | |
| | Final Loss | 0.572 | | |
| | Token Accuracy | ~94% | | |
| ## Files | |
| - `fsdp_checkpoint/` - FSDP2 distributed checkpoint | |
| - `adapter_config.json` - LoRA configuration | |
| - `tokenizer*` - Qwen2.5-72B tokenizer | |
| ## Note | |
| This is an FSDP2 checkpoint format. Load with HuggingFace accelerate library. | |