Downloads · 30 days
26
5% of all-time downloads
RichardErkhov/nbeerbower_-_SuperBruphin-3x7B-gguf
nbeerbower_-_SuperBruphin-3x7B-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
572
Public
Repo size
209 GB
Likes
0
Public
Click a slice to open those files.
.gguf242 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
SuperBruphin-3x7B - GGUF
| Name | Quant method | Size |
|---|---|---|
| SuperBruphin-3x7B.Q2_K.gguf | Q2_K | 6.33GB |
| SuperBruphin-3x7B.IQ3_XS.gguf | IQ3_XS | 7.08GB |
| SuperBruphin-3x7B.IQ3_S.gguf | IQ3_S | 7.48GB |
| SuperBruphin-3x7B.Q3_K_S.gguf | Q3_K_S | 7.46GB |
| SuperBruphin-3x7B.IQ3_M.gguf | IQ3_M | 7.63GB |
| SuperBruphin-3x7B.Q3_K.gguf | Q3_K | 8.28GB |
| SuperBruphin-3x7B.Q3_K_M.gguf | Q3_K_M | 8.28GB |
| SuperBruphin-3x7B.Q3_K_L.gguf | Q3_K_L | 8.98GB |
| SuperBruphin-3x7B.IQ4_XS.gguf | IQ4_XS | 9.32GB |
| SuperBruphin-3x7B.Q4_0.gguf | Q4_0 | 9.73GB |
| SuperBruphin-3x7B.IQ4_NL.gguf | IQ4_NL | 9.83GB |
| SuperBruphin-3x7B.Q4_K_S.gguf | Q4_K_S | 9.82GB |
| SuperBruphin-3x7B.Q4_K.gguf | Q4_K | 10.43GB |
| SuperBruphin-3x7B.Q4_K_M.gguf | Q4_K_M | 10.43GB |
| SuperBruphin-3x7B.Q4_1.gguf | Q4_1 | 10.8GB |
| SuperBruphin-3x7B.Q5_0.gguf | Q5_0 | 11.87GB |
| SuperBruphin-3x7B.Q5_K_S.gguf | Q5_K_S | 11.87GB |
| SuperBruphin-3x7B.Q5_K.gguf | Q5_K | 12.23GB |
| SuperBruphin-3x7B.Q5_K_M.gguf | Q5_K_M | 12.23GB |
| SuperBruphin-3x7B.Q5_1.gguf | Q5_1 | 12.94GB |
| SuperBruphin-3x7B.Q6_K.gguf | Q6_K | 14.15GB |
| SuperBruphin-3x7B.Q8_0.gguf | Q8_0 | 18.33GB |
license: apache-2.0 tags:
This is an experimental MoE model created using mergekit. (mixtral branch)
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: nbeerbower/bruphin-epsilon
gate_mode: hidden
dtype: bfloat16
experts:
- source_model: nbeerbower/bruphin-epsilon
positive_prompts:
- "Tell a story."
- source_model: FelixChao/WestSeverus-7B-DPO-v2
positive_prompts:
- "Solve this problem."
- source_model: jondurbin/airoboros-m-7b-3.1.2
positive_prompts:
- "Write a letter."
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 73.75 |
| AI2 Reasoning Challenge (25-Shot) | 71.16 |
| HellaSwag (10-Shot) | 87.74 |
| MMLU (5-Shot) | 64.58 |
| TruthfulQA (0-shot) | 66.85 |
| Winogrande (5-shot) | 81.53 |
| GSM8k (5-shot) | 70.66 |