Astrea-RP-v1-3B-GGUF/README.md

base_model, inference, language, library_name, license, model_creator, model_name, pipeline_tag, quantized_by, tags

base_model	inference	language	library_name	license	model_creator	model_name	pipeline_tag	quantized_by	tags
Aryanne/Astrea-RP-v1-3B	false	en	transformers	other	Aryanne	Astrea-RP-v1-3B	text-generation	afrideva	gpt llm large language model gguf ggml quantized q2_k q3_k_m q4_k_m q5_k_m q6_k q8_0

Aryanne/Astrea-RP-v1-3B-GGUF

Quantized GGUF model files for Astrea-RP-v1-3B from Aryanne

Name	Quant method	Size
astrea-rp-v1-3b.fp16.gguf	fp16	5.59 GB
astrea-rp-v1-3b.q2_k.gguf	q2_k	1.20 GB
astrea-rp-v1-3b.q3_k_m.gguf	q3_k_m	1.39 GB
astrea-rp-v1-3b.q4_k_m.gguf	q4_k_m	1.71 GB
astrea-rp-v1-3b.q5_k_m.gguf	q5_k_m	1.99 GB
astrea-rp-v1-3b.q6_k.gguf	q6_k	2.30 GB
astrea-rp-v1-3b.q8_0.gguf	q8_0	2.97 GB

Original Model Card:

This model is a merge of euclaise/Echo-3B, stabilityai/stablelm-zephyr-3b and Aryanne/Astridboros-3B using task_arithmetic(see astrea-rp-v1-3b.yml or below).

merge_method: task_arithmetic
base_model: euclaise/Ferret-3B
models:
  - model: euclaise/Ferret-3B
  - model: stabilityai/stablelm-zephyr-3b
    parameters:
      weight: 0.33
  - model: euclaise/Echo-3B
    parameters:
      weight: 0.66
  - model: Aryanne/Astridboros-3B
    parameters:
      weight: 0.16
dtype: float16

I recommend the use of Vicuna prompt format, but it's your choice to see what works for you.

I think zephyr license applies to this merge, for non commercial use.