NickyNicky/gemma-2b-it_oasst2_chatML_Cluster2_aya_multilingual_10k_prompts_ranked_all_json_V1

reference data model:

  datasets:
      link: https://huggingface.co/datasets/NickyNicky/oasst2_clusters

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

    base fine tune: NickyNicky/gemma-2b-it_oasst2_chatML_Cluster_2_V1

  Epoch: 2

  future experts: test

  Eval model:
    - link:
        soon

train/loss 0.5407

!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
!pip install flash-attn==2.5.5 --no-build-isolation

Version

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

How to use

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_Cluster2_aya_multilingual'
model_id= "NickyNicky/gemma-2b-it_oasst2_chatML_Cluster2_aya_multilingual_10k_prompts_ranked_all_json_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=2100
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])


prompt="""What were the main contributions of Eratosthenes to the development of mathematics in ancient Greece?"""

#EXAMPLE #1
input_text = f'''<bos><start_of_turn>system
You are a prompt evaluator response format json.
ngrams_length: "8" | cluster_length: "15".
lista de codigos linguisticos disponibles: ["en", "en"].<end_of_turn>
<start_of_turn>user
### |detect_prompt|:
{prompt}<end_of_turn>
<start_of_turn>model
'''

### OUTPUT EXAMPLE
'''
{
    "ngrams_length": "8",
    "ngrams": ["main", "contribution", "eratosthenes", "development", "mathematic", "ancient", "greece", "ancient greece"],
    "cluster_length": "15",
    "cluster": ["quantum", "magnetic", "star", "metal", "planet", "gravity", "force", "universe", "distance", "compound", "gravitational", "quantum computing", "solar", "sun", "earth"],
    "cluster_desc": ["Astrophysics", "Quantum Computing"],
    "avg_rating": "5.0",
    "kind": "synthetic"
    
}<end_of_turn><eos>
'''



inputs = tokenizer.encode(input_text,
                          return_tensors="pt",
                          add_special_tokens=False).to("cuda:0")
max_new_tokens=700
generation_config = GenerationConfig(
              max_new_tokens=max_new_tokens,
              temperature=0.32,
              #top_p=0.9,
              top_k=45,
              repetition_penalty=1.,  #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

code

https://colab.research.google.com/drive/1z26uLnTZWZ994G_dgyghNzh4hF2eEA6Z?usp=sharing

generated dataset model NickyNicky/prompts_ranked_808.

https://huggingface.co/datasets/NickyNicky/prompts_ranked_808