File size: 1,631 Bytes
ffabb0d 83637ec 8086ac9 ffabb0d 2611362 5c783f8 2611362 ffabb0d 83637ec |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
---
library_name: peft
license: mit
datasets:
- aloobun/mini-math23k-v1
tags:
- math
- phi
---
### WIP
## DONT USE THIS, ITS SHIT
## Usage:
```
import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
model_name = "microsoft/phi-1_5"
adapters_name = 'aloobun/phi_mini_math23k_v1'
model = AutoModelForCausalLM.from_pretrained(
model_name,
load_in_4bit=True,
torch_dtype=torch.bfloat16,
device_map="auto",
quantization_config=BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.bfloat16,
bnb_4bit_use_double_quant=True,
bnb_4bit_quant_type='nf4'
),
)
model = PeftModel.from_pretrained(model, adapters_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
```
```
prompt = "What is the largest two-digit integer whose digits are distinct and form a geometric sequence?"
formatted_prompt = (
f"### Instruction: {prompt} ### Response:"
)
inputs = tokenizer(formatted_prompt, return_tensors="pt").to("cuda:0")
outputs = model.generate(inputs=inputs.input_ids, max_new_tokens=1048)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```
## 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 0.5.0 |