Downloads · 30 days
187
7% of all-time downloads
RichardErkhov/liminerity_-_Smaug-slerp-30b-v0.1-gguf
liminerity_-_Smaug-slerp-30b-v0.1-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
187
7% of all-time downloads
All-time downloads
2.6K
Public
Repo size
348 GB
Likes
0
Public
Click a slice to open those files.
.gguf404 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Smaug-slerp-30b-v0.1 - GGUF
| Name | Quant method | Size |
|---|---|---|
| Smaug-slerp-30b-v0.1.Q2_K.gguf | Q2_K | 10.89GB |
| Smaug-slerp-30b-v0.1.IQ3_XS.gguf | IQ3_XS | 12.02GB |
| Smaug-slerp-30b-v0.1.IQ3_S.gguf | IQ3_S | 12.63GB |
| Smaug-slerp-30b-v0.1.Q3_K_S.gguf | Q3_K_S | 12.63GB |
| Smaug-slerp-30b-v0.1.IQ3_M.gguf | IQ3_M | 13.26GB |
| Smaug-slerp-30b-v0.1.Q3_K.gguf | Q3_K | 14.02GB |
| Smaug-slerp-30b-v0.1.Q3_K_M.gguf | Q3_K_M | 14.02GB |
| Smaug-slerp-30b-v0.1.Q3_K_L.gguf | Q3_K_L | 15.21GB |
| Smaug-slerp-30b-v0.1.IQ4_XS.gguf | IQ4_XS | 15.51GB |
| Smaug-slerp-30b-v0.1.Q4_0.gguf | Q4_0 | 16.24GB |
| Smaug-slerp-30b-v0.1.IQ4_NL.gguf | IQ4_NL | 16.33GB |
| Smaug-slerp-30b-v0.1.Q4_K_S.gguf | Q4_K_S | 16.36GB |
| Smaug-slerp-30b-v0.1.Q4_K.gguf | Q4_K | 17.27GB |
| Smaug-slerp-30b-v0.1.Q4_K_M.gguf | Q4_K_M | 17.27GB |
| Smaug-slerp-30b-v0.1.Q4_1.gguf | Q4_1 | 17.93GB |
| Smaug-slerp-30b-v0.1.Q5_0.gguf | Q5_0 | 19.63GB |
| Smaug-slerp-30b-v0.1.Q5_K_S.gguf | Q5_K_S | 19.63GB |
| Smaug-slerp-30b-v0.1.Q5_K.gguf | Q5_K | 20.16GB |
| Smaug-slerp-30b-v0.1.Q5_K_M.gguf | Q5_K_M | 20.16GB |
| Smaug-slerp-30b-v0.1.Q5_1.gguf | Q5_1 | 21.33GB |
| Smaug-slerp-30b-v0.1.Q6_K.gguf | Q6_K | 23.24GB |
| Smaug-slerp-30b-v0.1.Q8_0.gguf | Q8_0 | 30.1GB |
license: apache-2.0 tags:
Smaug-slerpB-v0.1 is a merge of the following models using mergekit:
slices:
- sources:
- model: abacusai/Smaug-72B-v0.1
layer_range: [0, 32]
- model: abacusai/Smaug-72B-v0.1
layer_range: [0, 32]
merge_method: slerp
base_model: abacusai/Smaug-72B-v0.1
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16