File size: 930 Bytes
8a914b1
 
 
 
563d486
 
 
00f146a
 
563d486
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
---
license: mit
tags:
- auto-gptq
- opt
- gptq
- 4bit
---

This model should use [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ) so you need to use `auto-gptq`

```py
from transformers import AutoTokenizer, pipeline, AutoModelForCausalLM, LlamaForCausalLM, LlamaTokenizer, StoppingCriteria, PreTrainedTokenizerBase
from auto_gptq import AutoGPTQForCausalLM

model_id = 'seonglae/opt-125m-4bit-gptq'
tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
model = AutoGPTQForCausalLM.from_quantized(
        model_id,
        model_basename=model_basename,
        trust_remote_code=True,
        device='cuda:0',
        use_triton=False,
        use_safetensors=True,
)

pipe = pipeline(
      "text-generation",
      model=model,
      tokenizer=tokenizer,
      temperature=0.5,
      top_p=0.95,
      max_new_tokens=100,
      repetition_penalty=1.15,
)
prompt = "USER: Are you AI?\nASSISTANT:"
pipe(prompt)
```