Update README.md

README.md

@@ -1,3 +1,209 @@
 
 
+
+
+---
+license: apache-2.0
+datasets:
+- NickyNicky/aya_dataset_multilingual_chatml_gemma_response_json
+model:
+- NickyNicky/gemma-2b-it_oasst2_chatML_Cluster_2_V1
+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.
+    solo responde en formato json.
+    lista de codigos linguisticos disponibles: ["es", "en", "fr", "de"].<end_of_turn>
+    <start_of_turn>user
+    {
+        "input": "fr",
+        "targets": "es",
+        "inputs_fr": "Quels président des États-Unis ne s’est jamais marié ?",
+    }<end_of_turn>
+    <start_of_turn>model\n
+    
+---
+
+
+![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
+
+    base fine tune: NickyNicky/gemma-2b-it_oasst2_chatML_Cluster_2_V1
+
+  Epoch: 2.5
+
+  future experts: 5
+
+  Eval model:
+    - link:
+        soon
+
+```
+
+
+## train/loss	0.2377
+
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/641b435ba5f876fe30c5ae0a/oCI0UQjJ1Rux2JXUHtEZB.png)
+
+
+## 
+
+
+```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_Cluster_2_aya_dataset_multilingual_chatml_response_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=1055
+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
+input_text = """James Buchanan es el único presidente que nunca se casó.”"""
+targets_traslate= "en"
+
+txt=f"""<bos><start_of_turn>system
+You are a helpful AI assistant.
+solo responde en formato json.
+lista de codigos linguisticos disponibles: ["es", "en", "fr", "de"].<end_of_turn>
+<start_of_turn>user
+{{
+    "input": "es",
+    "targets": "{targets_traslate}",
+    "inputs_es": "{input_text}",
+}}<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
+```