|
--- |
|
library_name: peft |
|
license: apache-2.0 |
|
datasets: |
|
- knkarthick/dialogsum |
|
pipeline_tag: summarization |
|
--- |
|
## About the Model |
|
|
|
LLama-2 7B is finetuned using SFT to generate summaries from conversations. |
|
|
|
|
|
|
|
## Useage with Transformers |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
import transformers |
|
from peft import PeftModel |
|
|
|
# Quantization config |
|
bnb_config = BitsAndBytesConfig( |
|
load_in_4bit=True, |
|
bnb_4bit_quant_type="nf4", |
|
bnb_4bit_compute_dtype="float16", |
|
) |
|
|
|
model_name = "TinyPixel/Llama-2-7B-bf16-sharded" |
|
|
|
# loading the model with quantization config |
|
model = AutoModelForCausalLM.from_pretrained( |
|
model_name, |
|
quantization_config=bnb_config, |
|
trust_remote_code=True, |
|
device_map='auto' |
|
) |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True , return_token_type_ids=False) |
|
tokenizer.pad_token = tokenizer.eos_token |
|
|
|
model = PeftModel.from_pretrained(model,"shenoy/DialogSumLlama2_qlora", device_map="auto") |
|
|
|
text = """### Instruction: |
|
Write a concise summary of the below input text.Return your response in bullet points which covers the key points of the text. |
|
### Input: |
|
#Person1#: Ms. Dawson, I need you to take a dictation for me. |
|
#Person2#: Yes, sir... |
|
#Person1#: This should go out as an intra-office memorandum to all employees by this afternoon. Are you ready? |
|
#Person2#: Yes, sir. Go ahead. |
|
#Person1#: Attention all staff... Effective immediately, all office communications are restricted to email correspondence and official memos. The use of Instant Message programs by employees during working hours is strictly prohibited. |
|
#Person2#: Sir, does this apply to intra-office communications only? Or will it also restrict external communications? |
|
#Person1#: It should apply to all communications, not only in this office between employees, but also any outside communications. |
|
#Person2#: But sir, many employees use Instant Messaging to communicate with their clients. |
|
#Person1#: They will just have to change their communication methods. I don't want any - one using Instant Messaging in this office. It wastes too much time! Now, please continue with the memo. Where were we? |
|
#Person2#: This applies to internal and external communications. |
|
#Person1#: Yes. Any employee who persists in using Instant Messaging will first receive a warning and be placed on probation. At second offense, the employee will face termination. Any questions regarding this new policy may be directed to department heads. |
|
#Person2#: Is that all? |
|
#Person1#: Yes. Please get this memo typed up and distributed to all employees before 4 pm. |
|
### Response :""" |
|
|
|
inputs = tokenizer(text, return_tensors="pt") |
|
outputs = model.generate(input_ids=inputs['input_ids'], attention_mask=inputs['attention_mask'], max_new_tokens=100 ,repetition_penalty=1.2) |
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
``` |
|
--- |
|
|
|
## Training procedure |
|
|
|
Training Configuration: |
|
|
|
- `per_device_train_batch_size`: 4 |
|
- `gradient_accumulation_steps`: 4 |
|
- `optim`: "paged_adamw_8bit" |
|
- `learning_rate`: 2e-4 |
|
- `lr_scheduler_type`: "linear" |
|
- `save_strategy`: "epoch" |
|
- `logging_steps`: 10 |
|
- `num_train_epochs`: 2 |
|
- `max_steps`: 50 |
|
- `fp16`: True |
|
|
|
LORA Configuration: |
|
|
|
- `lora_alpha`: 16 |
|
- `lora_dropout`: 0.05 |
|
- `target_modules`: ["q_proj", "v_proj"] |
|
- `r`: 8 |
|
- `bias`: "none" |
|
- `task_type`: "CAUSAL_LM" |
|
|
|
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: False |
|
- bnb_4bit_compute_dtype: float16 |
|
|
|
### Framework versions |
|
- `accelerate` 0.21.0 |
|
- `peft` 0.4.0 |
|
- `bitsandbytes` 0.40.2 |
|
- `transformers` 4.30.2 |
|
- `trl` 0.4.7 |
