File size: 1,020 Bytes
dc48904
 
12b0867
 
 
2097547
 
 
dc48904
8e82164
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
---
license: mit
tags:
- mergekit
- merge
base_model:
- moreh/MoMo-70B-lora-1.8.6-DPO
- moreh/MoMo-70B-lora-1.8.4-DPO
---

# MoMo-70B-lora-1.8.6-DPO based model with gradient slerp 

This is an English mixed Model based on
* [moreh/MoMo-70B-lora-1.8.6-DPO]

gpu code example

```
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import math

## v2 models
model_path = "kodonho/kodonho/Momo-70b-DPO-mixed"

tokenizer = AutoTokenizer.from_pretrained(model_path, use_default_system_prompt=False)
model = AutoModelForCausalLM.from_pretrained(
    model_path, torch_dtype=torch.float32, device_map='auto',local_files_only=False, load_in_4bit=True
)
print(model)
prompt = input("please input prompt:")
while len(prompt) > 0:
  input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")

  generation_output = model.generate(
    input_ids=input_ids, max_new_tokens=500,repetition_penalty=1.2
  )
  print(tokenizer.decode(generation_output[0]))
  prompt = input("please input prompt:")
```