Create README.md

README.md

@@ -0,0 +1,113 @@
+---
+model-index:
+- name: lince-zero
+  results: []
+license: apache-2.0
+language:
+- es
+thumbnail: https://huggingface.co/mrm8488/falcoder-7b/resolve/main/falcoder.png
+pipeline_tag: text-generation
+---
+
+<div style="text-align:center;width:250px;height:250px;">
+    <img src="https://huggingface.co/mrm8488/falcoder-7b/resolve/main/falcoder.png" alt="falcoder logo"">
+</div>
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Lince Zero 
+**Lince** is model fine-tuned on a massive and original corpus of Spanish instructions.
+
+## Model description 🧠
+
+TBA
+
+
+## Training and evaluation data 📚
+
+We created an instruction dataset following the format or popular datasets in the field such as *Alpaca* and Dolly* and augmented it.
+
+
+### Training hyperparameters ⚙
+
+TBA
+
+### Training results 🗒️
+
+TBA
+
+
+### Example of usage 👩‍💻
+```py
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, AutoTokenizer
+
+model_id = "clibrain/lince-zero"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+model = AutoModelForCausalLM.from_pretrained(model_id).to("cuda")
+
+
+def create_instruction(instruction: str, input_data: str = None, context: str = None) -> str:
+    sections = {
+        "Instrucción": instruction,
+        "Entrada": input_data,
+        "Contexto": context,
+    }
+
+    system_prompt = "A continuación hay una instrucción que describe una tarea, junto con una entrada que proporciona más contexto. Escriba una respuesta que complete adecuadamente la solicitud.\n\n"
+    prompt = system_prompt
+
+    for title, content in sections.items():
+        if content is not None:
+            prompt += f"### {title}:\n{content}\n\n"
+
+    prompt += "### Respuesta:\n"
+
+    return prompt
+
+
+
+def generate(
+        instruction,
+        input=None,
+        context=None,
+        max_new_tokens=128,
+        temperature=0.1,
+        top_p=0.75,
+        top_k=40,
+        num_beams=4,
+        **kwargs
+):
+    
+    prompt = create_instruction(instruction, input, context)
+    print(prompt)
+    inputs = tokenizer(prompt, return_tensors="pt")
+    input_ids = inputs["input_ids"].to("cuda")
+    attention_mask = inputs["attention_mask"].to("cuda")
+    generation_config = GenerationConfig(
+        temperature=temperature,
+        top_p=top_p,
+        top_k=top_k,
+        num_beams=num_beams,
+        **kwargs,
+    )
+    with torch.no_grad():
+        generation_output = model.generate(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            generation_config=generation_config,
+            return_dict_in_generate=True,
+            output_scores=True,
+            max_new_tokens=max_new_tokens,
+            early_stopping=True
+        )
+    s = generation_output.sequences[0]
+    output = tokenizer.decode(s)
+    return output.split("### Respuesta:")[1].lstrip("\n")
+
+instruction = "Dame una lista de lugares a visitar en España."
+print(generate(instruction))
+```