File size: 4,817 Bytes
8755dc4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2601f99
 
 
 
db8d789
8755dc4
 
 
 
 
 
 
 
 
 
 
 
 
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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
---
license: apache-2.0
datasets:
- OpenAssistant/oasst2
language:
- bg
- ca
- cs
- da
- de
- en
- es
- fr
- hr
- hu
- it
- nl
- pl
- pt
- ro
- ru
- sl
- sr
- sv
- uk

library_name: transformers

widget:
- text: |
    <bos><start_of_turn>system
    You are a helpful AI assistant.<end_of_turn>
    <start_of_turn>user
    What is the meaning of life in the current time?<end_of_turn>
    <start_of_turn>model
    
---


![image/png](https://cdn-uploads.huggingface.co/production/uploads/641b435ba5f876fe30c5ae0a/YXqUXFjX8uIJT-mdOnM1h.png)

```
reference data model:

  datasets:
    - lang: "bg,ca,cs,da,de,en,es,fr,hr,hu,it,nl,pl,pt,ro,ru,sl,sr,sv,uk"
      link: https://huggingface.co/datasets/NickyNicky/oasst2_clusters

  model:
    - google/gemma-2b-it
      Link:
        https://huggingface.co/google/gemma-2b-it

  Epoch: 7

  future experts: Cluster_3

  Eval model:
    - link:
        soon

```


## 


```Python
!python -m pip install --upgrade pip
!pip install "torch>=2.1.1" -U
!pip install torchaudio==2.2.0
!pip install -q datasets trl peft bitsandbytes sentencepiece wandb
!pip install -q accelerate safetensors deepspeed
!pip install -q scipy ninja -U
!pip install -q -U transformers==4.38.0
```


## Version
```py
import torch
torch.__version__
#OUTPUTS: ('2.2.0+cu121' )
```

## How to use
```py

from transformers import (
    AutoModelForCausalLM,
    AutoTokenizer,
    BitsAndBytesConfig,
    HfArgumentParser,
    TrainingArguments,
    pipeline,
    logging,
    GenerationConfig,
    TextIteratorStreamer,
)

from transformers import StoppingCriteria, StoppingCriteriaList

import torch

model_id='NickyNicky/gemma-2b-it_oasst2_chatML_Cluster_3_V1'

model = AutoModelForCausalLM.from_pretrained(model_id,
                                             device_map="auto",
                                             trust_remote_code=True,
                                             torch_dtype=torch.bfloat16,
                                             attn_implementation="flash_attention_2",
                                             # load_in_4bit=True,
                                             # low_cpu_mem_usage= True,

                                             )

max_length=2055
print("max_length",max_length)


tokenizer = AutoTokenizer.from_pretrained(model_id,
                                          # use_fast = False,
                                          max_length=max_length,)


class ListOfTokensStoppingCriteria(StoppingCriteria):
    """
    Clase para definir un criterio de parada basado en una lista de tokens específicos.
    """
    def __init__(self, tokenizer, stop_tokens):
        self.tokenizer = tokenizer
        # Codifica cada token de parada y guarda sus IDs en una lista
        self.stop_token_ids_list = [tokenizer.encode(stop_token, add_special_tokens=False) for stop_token in stop_tokens]

    def __call__(self, input_ids, scores, **kwargs):
        # Verifica si los últimos tokens generados coinciden con alguno de los conjuntos de tokens de parada
        for stop_token_ids in self.stop_token_ids_list:
            len_stop_tokens = len(stop_token_ids)
            if len(input_ids[0]) >= len_stop_tokens:
                if input_ids[0, -len_stop_tokens:].tolist() == stop_token_ids:
                    return True
        return False

# Uso del criterio de parada personalizado
stop_tokens = ["<end_of_turn>"]  # Lista de tokens de parada

# Inicializa tu criterio de parada con el tokenizer y la lista de tokens de parada
stopping_criteria = ListOfTokensStoppingCriteria(tokenizer, stop_tokens)

# Añade tu criterio de parada a una StoppingCriteriaList
stopping_criteria_list = StoppingCriteriaList([stopping_criteria])



#EXAMPLE #1
txt="""<bos><start_of_turn>system
You are a helpful AI assistant.<end_of_turn>
<start_of_turn>user
Me dices los diferentes tipos de reciclaje que suelen existir en las ciudades europeas<end_of_turn>
<start_of_turn>model
"""

#EXAMPLE #2
txt="""<bos><start_of_turn>system
You are a helpful AI assistant.<end_of_turn>
<start_of_turn>user
What is the meaning of life in the current time?<end_of_turn>
<start_of_turn>model
"""


inputs = tokenizer.encode(txt,
                          return_tensors="pt",
                          add_special_tokens=False).to("cuda:0")
max_new_tokens=1000
generation_config = GenerationConfig(
              max_new_tokens=max_new_tokens,
              temperature=0.55,
              #top_p=0.9,
              #top_k=len_tokens,
              repetition_penalty=1.1, 
              do_sample=True,
          )
outputs = model.generate(generation_config=generation_config,
                         input_ids=inputs,
                         stopping_criteria=stopping_criteria_list,)
tokenizer.decode(outputs[0], skip_special_tokens=False) #True
```