Downloads · 30 days
78
3% of all-time downloads
RichardErkhov/Aryanne_-_Astrea-RP-v1.5-3B-gguf
Aryanne_-_Astrea-RP-v1.5-3B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
78
3% of all-time downloads
All-time downloads
2.3K
Public
Repo size
32.1 GB
Likes
1
Public
Click a slice to open those files.
.gguf37.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Astrea-RP-v1.5-3B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Astrea-RP-v1.5-3B.Q2_K.gguf | Q2_K | 1.01GB |
| Astrea-RP-v1.5-3B.IQ3_XS.gguf | IQ3_XS | 1.11GB |
| Astrea-RP-v1.5-3B.IQ3_S.gguf | IQ3_S | 1.17GB |
| Astrea-RP-v1.5-3B.Q3_K_S.gguf | Q3_K_S | 1.17GB |
| Astrea-RP-v1.5-3B.IQ3_M.gguf | IQ3_M | 1.23GB |
| Astrea-RP-v1.5-3B.Q3_K.gguf | Q3_K | 1.3GB |
| Astrea-RP-v1.5-3B.Q3_K_M.gguf | Q3_K_M | 1.3GB |
| Astrea-RP-v1.5-3B.Q3_K_L.gguf | Q3_K_L | 1.4GB |
| Astrea-RP-v1.5-3B.IQ4_XS.gguf | IQ4_XS | 1.43GB |
| Astrea-RP-v1.5-3B.Q4_0.gguf | Q4_0 | 1.5GB |
| Astrea-RP-v1.5-3B.IQ4_NL.gguf | IQ4_NL | 1.51GB |
| Astrea-RP-v1.5-3B.Q4_K_S.gguf | Q4_K_S | 1.51GB |
| Astrea-RP-v1.5-3B.Q4_K.gguf | Q4_K | 1.59GB |
| Astrea-RP-v1.5-3B.Q4_K_M.gguf | Q4_K_M | 1.59GB |
| Astrea-RP-v1.5-3B.Q4_1.gguf | Q4_1 | 1.65GB |
| Astrea-RP-v1.5-3B.Q5_0.gguf | Q5_0 | 1.81GB |
| Astrea-RP-v1.5-3B.Q5_K_S.gguf | Q5_K_S | 1.81GB |
| Astrea-RP-v1.5-3B.Q5_K.gguf | Q5_K | 1.86GB |
| Astrea-RP-v1.5-3B.Q5_K_M.gguf | Q5_K_M | 1.86GB |
| Astrea-RP-v1.5-3B.Q5_1.gguf | Q5_1 | 1.96GB |
| Astrea-RP-v1.5-3B.Q6_K.gguf | Q6_K | 2.14GB |
| Astrea-RP-v1.5-3B.Q8_0.gguf | Q8_0 | 2.77GB |
base_model:
This is a merge of pre-trained language models created using mergekit.
This model was merged using the passthrough merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: task_arithmetic
base_model: Aryanne/Astrea-RP-v1-3B
models:
- model: Aryanne/Astrea-RP-v1-3B
parameters:
weight: 0.7
- model: Aryanne/Astrohermes-3B+jeiku/No_Robots_Alpaca_StableLM
parameters:
weight: 0.35
- model: jeiku/Rosa_v1_3B+jeiku/smol_PIPPA_StableLM
parameters:
weight: 0.33
- model: Walmart-the-bag/zephyr-quiklang-3b-4K+jeiku/Bluemoon_cleaned_StableLM
parameters:
weight: 0.38
dtype: float16
I think zephyr license applies to this merge, for non commercial use.
Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.