metadata

license: llama2
library_name: transformers
pipeline_tag: text-generation
tags:
  - quantized
  - Uncensored
  - LLama2
  - Instruct
language:
  - en

LLaMa_V2-13B-Instruct-Uncensored-GGML

Quantized LLaMa.V2 13B model weights - Instruction based

Big thank you to Eric Hartford for his work aiding the creation of datasets such as:
- wizardlm_evol_instruct_V2_196k_unfiltered_merged_split
- wizard_vicuna_70k_unfiltered

Such datasets play a big role in accurately addressing model biases, without sacrificing performance

Provided Files:

Quantised:

LLaMa_V2-13B-Instruct-Uncensored-q4_0-GGML.bin

LLaMa_V2-13B-Instruct-Uncensored-q4_1-GGML.bin

LLaMa_V2-13B-Instruct-Uncensored-q5_0-GGML.bin

Unquantised:

LLaMa_V2-13B-Instruct-Uncensored-f16-Unquantized-GGML.bin