|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- code |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
|
|
|
# Model Card for Model ID |
|
|
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
|
|
|
|
|
|
|
|
## Model Description |
|
|
Developed by: LeanAI |
|
|
|
|
|
Model type: text-generation |
|
|
|
|
|
Finetuned from model: Trelis/Llama-2-7b-chat-hf-sharded-bf16 |
|
|
|
|
|
Model Sources: Llama-2-7b |
|
|
|
|
|
## Licensing and Usage |
|
|
|
|
|
Llama 2 license |
|
|
|
|
|
This model is bound by the license & usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind. |
|
|
|
|
|
## Dataset |
|
|
|
|
|
The dataset used for training this model: |
|
|
https://www.kaggle.com/datasets/linkanjarad/coding-problems-and-solution-python-code |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
|
|
|
The following `bitsandbytes` quantization config was used during training: |
|
|
- quant_method: bitsandbytes |
|
|
- 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: float16 |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.6.0.dev0 |
|
|
|
