|
--- |
|
library_name: peft |
|
--- |
|
## 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: fp4 |
|
- bnb_4bit_use_double_quant: False |
|
- bnb_4bit_compute_dtype: float32 |
|
|
|
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: False |
|
- bnb_4bit_compute_dtype: bfloat16 |
|
### Framework versions |
|
|
|
- PEFT 0.5.0 |
|
|
|
- PEFT 0.5.0 |
|
|
|
## How to Use |
|
|
|
You can load the model and perform inference as follows: |
|
|
|
```python |
|
from transformers import AutoTokenizer , AutoModelForCausalLM |
|
from peft import PeftConfig , PeftModel |
|
|
|
|
|
path_or_model_name="llama2-frenchmedmcqa-dpo" |
|
|
|
config = PeftConfig.from_pretrained(path_or_model_name) |
|
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_4bit=True, device_map='auto') |
|
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path) |
|
model = PeftModel.from_pretrained(model ,path_or_model_name) |
|
|
|
prompt="### Human: Quelle méthode peut être utilisée pour déterminer la constante d'acidité (7,1 et 10,6) de l'acide valproïque (acide dipropylacétique) ? .\n### Assistant : " |
|
|
|
input_ids =tokenizer(prompt , return_tensors="pt") |
|
output= model.generate(**input_ids , max_length=120) |
|
text_generated =tokenizer.decode(output[0] , skip_special_tokens=True) |
|
|
|
print(text_generated) |
|
``` |
