README.md

metadata

base_model: Aryanne/Zephyr-3.43B
inference: false
language:
  - en
library_name: transformers
license: other
model_creator: Aryanne
model_name: Zephyr-3.43B
pipeline_tag: text-generation
quantized_by: afrideva
tags:
  - merge
  - llm
  - stablelm
  - gguf
  - ggml
  - quantized
  - q2_k
  - q3_k_m
  - q4_k_m
  - q5_k_m
  - q6_k
  - q8_0

Aryanne/Zephyr-3.43B-GGUF

Quantized GGUF model files for Zephyr-3.43B from Aryanne

Name	Quant method	Size
zephyr-3.43b.fp16.gguf	fp16	6.86 GB
zephyr-3.43b.q2_k.gguf	q2_k	1.46 GB
zephyr-3.43b.q3_k_m.gguf	q3_k_m	1.70 GB
zephyr-3.43b.q4_k_m.gguf	q4_k_m	2.09 GB
zephyr-3.43b.q5_k_m.gguf	q5_k_m	2.44 GB
zephyr-3.43b.q6_k.gguf	q6_k	2.82 GB
zephyr-3.43b.q8_0.gguf	q8_0	3.65 GB

Original Model Card:

This model is a merge/fusion of Aryanne/Astridboros-3B and stabilityai/stablelm-zephyr-3b , 28 layers of Zephyr + 12 layers of Astridboros together(see zephyr-3.43b.yml or below).

A total of 40 layers, with 3.43B of parameters.

License it's the same as Zephyr cause it has 70% of it.

slices:
  - sources:
    - model: stabilityai/stablelm-zephyr-3b
      layer_range: [0, 14] 
  - sources:
    - model: Aryanne/Astridboros-3B
      layer_range: [10, 22]
  - sources:
    - model: stabilityai/stablelm-zephyr-3b
      layer_range: [18, 32]
merge_method: passthrough
dtype: float16

I recommend the use of the Zephyr prompt format.

<|user|>
List 3 synonyms for the word "tiny"<|endoftext|>
<|assistant|>
1. Dwarf
2. Little
3. Petite<|endoftext|>

GGUF Quants: [notyet](not yet)