File size: 1,574 Bytes
4934002 380ced9 4934002 7d78035 4934002 346645d 8ec9a4f 346645d 8ec9a4f 380ced9 8ec9a4f 4934002 |
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 |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
<!-- Provide a longer summary of what this model is. -->
This is the model card of a Phi-2 model trained on a synthetic data set to solve step by guid to solve a riddle or answer any kind of question
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Requiremnts
```python
!pip install -U transformers bitsandbytes einops accelerate peft datasets wandb
```
### Direct Use
```python
import torch
from transformers import AutoModelForCausalLM, BitsAndBytesConfig, set_seed
# set seed
set_seed(42)
# Load model
modelpath = "DisgustingOzil/phi-2-riddler"
model = AutoModelForCausalLM.from_pretrained(
modelpath,
device_map="auto",
quantization_config=BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_compute_dtype=torch.float16,
bnb_4bit_quant_type="nf4",
),
torch_dtype=torch.float16,
)
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(modelpath, use_fast=False)
question = "Why life is so difficult of life?"
messages = [
{"role": "user", "content": question},
]
input_tokens = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to("cuda")
output_tokens = model.generate(input_tokens, max_new_tokens=200)
output = tokenizer.decode(output_tokens[0])
print(output)
```
|