|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
library_name: peft |
|
base_model: databricks/dolly-v2-3b |
|
--- |
|
## 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 |
|
|
|
### Import Model |
|
```python |
|
import torch |
|
from peft import PeftModel, PeftConfig |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
peft_model_id = "AhmedBou/databricks-dolly-v2-3b_for_clinical_terms_synonyms" |
|
config = PeftConfig.from_pretrained(peft_model_id) |
|
model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True, load_in_8bit=True, device_map='auto') |
|
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path) |
|
|
|
# Load the Lora model |
|
model = PeftModel.from_pretrained(model, peft_model_id) |
|
``` |
|
|
|
### Model Inference |
|
|
|
```python |
|
input_text = "participant safety -->: " |
|
batch = tokenizer(input_text, return_tensors='pt') |
|
|
|
with torch.cuda.amp.autocast(): |
|
output_tokens = model.generate(**batch, max_new_tokens=50) |
|
|
|
print('\n\n', tokenizer.decode(output_tokens[0], skip_special_tokens=True)) |
|
``` |