Downloads · 30 days
26
5% of all-time downloads
RichardErkhov/liminerity_-_dhbacmes-3b-slerp-gguf
liminerity_-_dhbacmes-3b-slerp-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
26
5% of all-time downloads
All-time downloads
577
Public
Repo size
36.1 GB
Likes
0
Public
Click a slice to open those files.
.gguf41.9 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
dhbacmes-3b-slerp - GGUF
| Name | Quant method | Size |
|---|---|---|
| dhbacmes-3b-slerp.Q2_K.gguf | Q2_K | 1.21GB |
| dhbacmes-3b-slerp.IQ3_XS.gguf | IQ3_XS | 1.32GB |
| dhbacmes-3b-slerp.IQ3_S.gguf | IQ3_S | 1.38GB |
| dhbacmes-3b-slerp.Q3_K_S.gguf | Q3_K_S | 1.38GB |
| dhbacmes-3b-slerp.IQ3_M.gguf | IQ3_M | 1.44GB |
| dhbacmes-3b-slerp.Q3_K.gguf | Q3_K | 1.49GB |
| dhbacmes-3b-slerp.Q3_K_M.gguf | Q3_K_M | 1.49GB |
| dhbacmes-3b-slerp.Q3_K_L.gguf | Q3_K_L | 1.57GB |
| dhbacmes-3b-slerp.IQ4_XS.gguf | IQ4_XS | 1.59GB |
| dhbacmes-3b-slerp.Q4_0.gguf | Q4_0 | 1.65GB |
| dhbacmes-3b-slerp.IQ4_NL.gguf | IQ4_NL | 1.66GB |
| dhbacmes-3b-slerp.Q4_K_S.gguf | Q4_K_S | 1.71GB |
| dhbacmes-3b-slerp.Q4_K.gguf | Q4_K | 1.83GB |
| dhbacmes-3b-slerp.Q4_K_M.gguf | Q4_K_M | 1.83GB |
| dhbacmes-3b-slerp.Q4_1.gguf | Q4_1 | 1.81GB |
| dhbacmes-3b-slerp.Q5_0.gguf | Q5_0 | 1.96GB |
| dhbacmes-3b-slerp.Q5_K_S.gguf | Q5_K_S | 1.99GB |
| dhbacmes-3b-slerp.Q5_K.gguf | Q5_K | 2.09GB |
| dhbacmes-3b-slerp.Q5_K_M.gguf | Q5_K_M | 2.09GB |
| dhbacmes-3b-slerp.Q5_1.gguf | Q5_1 | 2.12GB |
| dhbacmes-3b-slerp.Q6_K.gguf | Q6_K | 2.42GB |
| dhbacmes-3b-slerp.Q8_0.gguf | Q8_0 | 2.98GB |
license: apache-2.0 tags:
dhbacmes-3b-slerp is a merge of the following models using mergekit:
slices:
- sources:
- model: liminerity/herbaccbaccules-3b-slerp
layer_range: [0, 40]
- model: KnutJaegersberg/Deita-2b
layer_range: [0, 40]
merge_method: slerp
base_model: liminerity/herbaccbaccules-3b-slerp
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: float16
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 53.02 |
| AI2 Reasoning Challenge (25-Shot) | 45.22 |
| HellaSwag (10-Shot) | 70.77 |
| MMLU (5-Shot) | 52.94 |
| TruthfulQA (0-shot) | 40.41 |
| Winogrande (5-shot) | 65.11 |
| GSM8k (5-shot) | 43.67 |