README.md

metadata

base_model: cnmoro/ahxt_llama2_xs_460M_experimental_ptbr_instruct
inference: false
language:
  - en
  - pt
model_creator: cnmoro
model_name: ahxt_llama2_xs_460M_experimental_ptbr_instruct
pipeline_tag: text-generation
quantized_by: afrideva
tags:
  - gguf
  - ggml
  - quantized
  - q2_k
  - q3_k_m
  - q4_k_m
  - q5_k_m
  - q6_k
  - q8_0
widget:
  - text: |
      ### Instruction: 
      Sua instrução aqui

      ### Response:

cnmoro/ahxt_llama2_xs_460M_experimental_ptbr_instruct-GGUF

Quantized GGUF model files for ahxt_llama2_xs_460M_experimental_ptbr_instruct from cnmoro

Name	Quant method	Size
ahxt_llama2_xs_460m_experimental_ptbr_instruct.fp16.gguf	fp16	925.45 MB
ahxt_llama2_xs_460m_experimental_ptbr_instruct.q2_k.gguf	q2_k	212.56 MB
ahxt_llama2_xs_460m_experimental_ptbr_instruct.q3_k_m.gguf	q3_k_m	238.87 MB
ahxt_llama2_xs_460m_experimental_ptbr_instruct.q4_k_m.gguf	q4_k_m	288.52 MB
ahxt_llama2_xs_460m_experimental_ptbr_instruct.q5_k_m.gguf	q5_k_m	333.29 MB
ahxt_llama2_xs_460m_experimental_ptbr_instruct.q6_k.gguf	q6_k	380.87 MB
ahxt_llama2_xs_460m_experimental_ptbr_instruct.q8_0.gguf	q8_0	492.67 MB

Original Model Card:

Finetuned version of ahxt/llama2_xs_460M_experimental

Using a PTBR Instruct dataset.

Just like ahxt's, this is experimental and for research purposes only