Downloads · 30 days
13
4% of all-time downloads
qwen14-2wc1p-eos-3-merge
Steven10429/qwen14-2wc1p-eos-3-merge
qwen14-2wc1p-eos-3-merge is a text generation model from Steven10429. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
All-time downloads
361
Public
Parameters
14.8B
150 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf91.2 GB · 61%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- qwen2
- Access
- Public
- Created
- Feb 15, 2025
- Updated
- Feb 18, 2025
- SHA
- 98ee3f29
Base models
Model card
From the Hugging Face model README
Model
Steven10429/qwen14-2wc1p-eos-3-merge
Details:
- base_model: Steven10429/qwen14b-2wc1p-pj3ha_qwen14b-generic-eos-2
- lora_model: Steven10429/qwen14-2wc1p-eos-3
- quant_methods: ['Q2_K', 'Q4_K', 'IQ4_NL', 'Q5_K_M', 'Q6_K', 'Q8_0']
- created_at: 2025-02-13 21:45:06
- created_by: Steven10429/apply_lora_and_quantize
This iteration
本轮训练
- 开启eos
- 降低lr
- 3 epoch
- 尝试改善模型生成长度问题
下一步尝试：
- 随机EOS出现，0.3概率出现EOS
- 降低EOS的概率，修改GUFF保存文件
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- other
- Created
- Feb 15, 2025
- Updated
- Feb 18, 2025