|
--- |
|
library_name: peft |
|
license: apache-2.0 |
|
--- |
|
# minihf_evaluator_openllama_7b |
|
|
|
`minihf_evaluator_openllama_7b` is a LoRA instruct fine-tune of [OpenLLaMA 7B](https://huggingface.co/openlm-research/open_llama_7b). |
|
|
|
The sequence `<|end|>` was used to separate the prompt and response. The correct way to prompt the model is: `Does 2 + 2 = 4?<|end|>`. The tokenizer will prepend a BOS token (`<s>`) by default. The response will end with an EOS token (`</s>`). |
|
|
|
## Training procedure |
|
|
|
`minihf_evaluator_openllama_7b` was fine-tuned for 100,000 examples on 90% [Muennighoff/flan](https://huggingface.co/datasets/Muennighoff/flan) / 10% [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) using batch size 4 per GPU on 8 40GB A100 GPUs. Examples where the prompt and response would not fit into 2,048 tokens were dropped. The fine-tuning was done using the following command: |
|
|
|
```bash |
|
accelerate launch make_evaluator.py --output-dir minihf_evaluator_openllama_7b |
|
``` |
|
|
|
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 |
|
|
