|
--- |
|
library_name: peft |
|
datasets: |
|
- EleutherAI/wikitext_document_level |
|
language: |
|
- en |
|
--- |
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
|
|
LLaMA 33b finetuned on `wikitext_document_level` with a combination of both linear and NTK-aware ROPE scaling. |
|
|
|
Trained with alpha=4, scale=2. |
|
|
|
<img src="llama33b-s2a4-qlora/resolve/main/perplexity.png" alt="Perplexity Graph" /> |
|
|
|
## Training procedure |
|
|
|
|
|
The following `bitsandbytes` quantization config was used during training: |
|
- load_in_8bit: False |
|
- load_in_4bit: True |
|
- llm_int8_threshold: 6.0 |
|
- llm_int8_skip_modules: None |
|
- llm_int8_enable_fp32_cpu_offload: False |
|
- llm_int8_has_fp16_weight: False |
|
- bnb_4bit_quant_type: nf4 |
|
- bnb_4bit_use_double_quant: True |
|
- bnb_4bit_compute_dtype: bfloat16 |
|
### Framework versions |
|
|
|
|
|
- PEFT 0.4.0.dev0 |
|
|
