---
library_name: transformers
tags:
- synthetic
license: apache-2.0
datasets:
- teknium/OpenHermes-2.5
- Iker/OpenHermes-2.5-Spanish
- projecte-aina/RAG_Multilingual
- Iker/Document-Translation-en-es
- Iker/InstructTranslation-EN-ES
- Helsinki-NLP/opus-100
- glaiveai/glaive-code-assistant-v3
- glaiveai/glaive-function-calling-v2
language:
- es
- en
pipeline_tag: text-generation
base_model: google/gemma-2b
---


![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/614a1ebb8f82f1df64d55126/2i_CasoeJTgQPNoBIfA8E.jpeg)


# Neurona 2B Beta: Un Modelo de Lenguage en Español

> Esta es una versión preliminar del dataset card. El modelo está en desarrollo y no es la versión final. Si quieres saber más sobre este modelo, escribe a iker.garciaf@ehu.eus


Neurona 2B es un modelo de lenguaje en Español. Esta es la primera iteración y un experimento para poner a punto los scripts y la infraestructura. 

Neurona 2B ha sido entrenado con los siguiente datasets

- [teknium/OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5)
- [Iker/OpenHermes-2.5-Spanish](https://huggingface.co/datasets/Iker/OpenHermes-2.5-Spanish)
- [Iker/Document-Translation-en-es](https://huggingface.co/datasets/Iker/Document-Translation-en-es)
- [Iker/InstructTranslation-EN-ES](https://huggingface.co/datasets/Iker/InstructTranslation-EN-ES)
- [Helsinki-NLP/opus-100 (en-es, only a few examples to reach 1 million instructions)](https://huggingface.co/datasets/Helsinki-NLP/opus-100)
- [projecte-aina/RAG_Multilingual(es only, 3701 examples)](https://huggingface.co/datasets/projecte-aina/RAG_Multilingual)
- [glaiveai/glaive-code-assistant-v3](https://huggingface.co/datasets/glaiveai/glaive-code-assistant-v3)
- [glaiveai/glaive-function-calling-v2](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2)

Esta mezcla de datasets en Inglés y Español, permite al modelo adquirir diferentes capacidades, como RAG, function calling, code assistant, question answering, summarization... tanto en Inglés como en Español. 

# Entrenamiento

Este modelo se ha entrado usando 4xNvidia A100 80Gb y axolotl
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)

Esta es la configuración usada

```yaml
base_model: google/gemma-2b
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
is_falcon_derived_model:
is_llama_derived_model:
is_qwen_derived_model:
is_mistral_derived_model:

load_in_8bit: false
load_in_4bit: false
strict: false

device_map: null

datasets:
  - path: /ikerlariak/igarcia945/Mortadelo-Filemon/final_dataset/OpenHermes-2.5-Spanish_fix_gpt.jsonl
    type: sharegpt
    conversation: chatml
    field: conversations
    roles:
      input:
        - system
        - gpt
      output:
        - human
  - path: /ikerlariak/igarcia945/Mortadelo-Filemon/final_dataset/OpenHermes-2.5-English.jsonl
    type: sharegpt
    conversation: chatml
    field: conversations
  - path: /ikerlariak/igarcia945/Mortadelo-Filemon/final_dataset/glaive-function-calling-v2.jsonl
    type: sharegpt
    conversation: chatml
    field: conversations
    roles:
      input:
        - system
        - gpt
        - tool
      output:
        - human
  - path: /ikerlariak/igarcia945/Mortadelo-Filemon/final_dataset/glaive-code-assistant-v3-small.jsonl
    type: sharegpt
    conversation: chatml
    field: conversations
    roles:
      input:
        - system
        - gpt
      output:
        - human
chat_template: chatml

dataset_prepared_path: /ikerlariak/igarcia945/Mortadelo-Filemon/gemma-2b-spanish/dataset

shuffle_merged_datasets: true

val_set_size: 0.005

output_dir: /ikerlariak/igarcia945/Mortadelo-Filemon/gemma-2b-spanish/

adapter:
lora_model_dir:

sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: false

special_tokens:
  bos_token: "<|im_start|>"
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"

tokens:
  - "<|begin_of_text|>"
  - "<|end_of_text|>"
  - "<|im_start|>"
  - "<|im_end|>"
  - "<|start_header_id|>"
  - "<|end_header_id|>"
  - "<tool_call>"
  - "<tool_response>"
  - "<tools>"
  - "</tool_call>"
  - "</tool_response>"
  - "</tools>"
  - "<reserved1>"
  - "<reserved2>"
  - "<reserved3>"
  - "<reserved4>"



neftune_noise_alpha: 5

wandb_project: Mortadelo&Filemon
wandb_entity: igarciaf
wandb_watch:
wandb_name: gemma2b
wandb_log_model: 

gradient_accumulation_steps: 32
micro_batch_size: 2
eval_batch_size: 2
num_epochs: 3
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.00007


train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.03
evals_per_epoch: 4
eval_table_size:
save_strategy: "no"
debug:
deepspeed: /ikerlariak/igarcia945/Mortadelo-Filemon/train_configs/deepspeed_zero3.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

seed: 33
```