22 lines
670 B
Markdown
22 lines
670 B
Markdown
|
---
|
||
|
|
language: en
|
||
|
|
license: apache-2.0
|
||
|
|
library_name: transformers
|
||
|
|
---
|
||
|
|
|
||
|
|
# Quantized Fine-tuned Model: sqft-phi-3.5-mini-instruct-wikitext2-awq-64g-ppl10.41
|
||
|
|
|
||
|
|
- Source Model: [IntelLabs/sqft-phi-3.5-mini-instruct-wikitext2-ppl9.78](https://huggingface.co/IntelLabs/sqft-phi-3.5-mini-instruct-wikitext2-ppl9.78)
|
||
|
|
- Finetuning Method: NLS
|
||
|
|
- Adapter Version: Heuristic
|
||
|
|
- Quantization: AWQ-INT4 (group size: 64)
|
||
|
|
|
||
|
|
### Evaluation
|
||
|
|
|
||
|
|
```bash
|
||
|
|
CUDA_VISIBLE_DEVICES=$DEVICES lm_eval --model hf --model_args pretrained=IntelLabs/sqft-phi-3.5-mini-instruct-wikitext2-awq-64g-ppl10.41,max_length=4096 --tasks wikitext --batch_size auto:4 --output_path result.json
|
||
|
|
```
|
||
|
|
|
||
|
|
## License
|
||
|
|
|
||
|
|
Apache-2.0
|