CoolFace
Modelpublic

RichardErkhov/chargoddard_-_llama-polyglot-13b-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes199downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-polyglot-13b - GGUF

  • —Model creator: https://huggingface.co/chargoddard/
  • —Original model: https://huggingface.co/chargoddard/llama-polyglot-13b/
NameQuant methodSize
llama-polyglot-13b.Q2_K.ggufQ2_K4.52GB
llama-polyglot-13b.IQ3_XS.ggufIQ3_XS4.99GB
llama-polyglot-13b.IQ3_S.ggufIQ3_S5.27GB
llama-polyglot-13b.Q3_K_S.ggufQ3KS5.27GB
llama-polyglot-13b.IQ3_M.ggufIQ3_M5.57GB
llama-polyglot-13b.Q3_K.ggufQ3_K5.9GB
llama-polyglot-13b.Q3_K_M.ggufQ3KM5.9GB
llama-polyglot-13b.Q3_K_L.ggufQ3KL6.45GB
llama-polyglot-13b.IQ4_XS.ggufIQ4_XS6.54GB
llama-polyglot-13b.Q4_0.ggufQ4_06.86GB
llama-polyglot-13b.IQ4_NL.ggufIQ4_NL6.9GB
llama-polyglot-13b.Q4_K_S.ggufQ4KS6.91GB
llama-polyglot-13b.Q4_K.ggufQ4_K7.33GB
llama-polyglot-13b.Q4_K_M.ggufQ4KM7.33GB
llama-polyglot-13b.Q4_1.ggufQ4_17.61GB
llama-polyglot-13b.Q5_0.ggufQ5_08.36GB
llama-polyglot-13b.Q5_K_S.ggufQ5KS8.36GB
llama-polyglot-13b.Q5_K.ggufQ5_K8.6GB
llama-polyglot-13b.Q5_K_M.ggufQ5KM8.6GB
llama-polyglot-13b.Q5_1.ggufQ5_19.1GB
llama-polyglot-13b.Q6_K.ggufQ6_K9.95GB
llama-polyglot-13b.Q8_0.ggufQ8_012.88GB

Original model description: --- license: llama2 tags:

  • —llama2
  • —merge
  • —mergekit ---

Experimental multi-lingual model using a new merge technique.

Mergekit configuration (experimental branch):

yaml
models:
  - model: clibrain/Llama-2-13b-ft-instruct-es
  - model: LeoLM/leo-hessianai-13b
  - model: daekeun-ml/Llama-2-ko-DPO-13B
  - model: pleisto/yuren-13b-chatml
  - model: bofenghuang/vigogne-2-13b-instruct
  - model: OpenBuddy/openbuddy-llama2-13b-v8.1-fp16
merge_method: dare_ties
base_model: TheBloke/Llama-2-13B-fp16
dtype: float16
parameters:
  density: 0.3
  weight: 1.0
  normalize: true
  int8_mask: true
tokenizer_source: base