Downloads · 30 days
38
3% of all-time downloads
RichardErkhov/ibndias_-_Nous-Hermes-2-MoE-2x34B-gguf
ibndias_-_Nous-Hermes-2-MoE-2x34B-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
38
3% of all-time downloads
All-time downloads
1.3K
Public
Repo size
608 GB
Likes
0
Public
Click a slice to open those files.
.gguf677 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Nous-Hermes-2-MoE-2x34B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Nous-Hermes-2-MoE-2x34B.Q2_K.gguf | Q2_K | 20.86GB |
| Nous-Hermes-2-MoE-2x34B.Q3_K_S.gguf | Q3_K_S | 24.51GB |
| Nous-Hermes-2-MoE-2x34B.Q3_K.gguf | Q3_K | 27.23GB |
| Nous-Hermes-2-MoE-2x34B.Q3_K_M.gguf | Q3_K_M | 27.23GB |
| Nous-Hermes-2-MoE-2x34B.Q3_K_L.gguf | Q3_K_L | 29.59GB |
| Nous-Hermes-2-MoE-2x34B.IQ4_XS.gguf | IQ4_XS | 26.59GB |
| Nous-Hermes-2-MoE-2x34B.Q4_0.gguf | Q4_0 | 31.98GB |
| Nous-Hermes-2-MoE-2x34B.IQ4_NL.gguf | IQ4_NL | 32.27GB |
| Nous-Hermes-2-MoE-2x34B.Q4_K_S.gguf | Q4_K_S | 32.22GB |
| Nous-Hermes-2-MoE-2x34B.Q4_K.gguf | Q4_K | 32.38GB |
| Nous-Hermes-2-MoE-2x34B.Q4_K_M.gguf | Q4_K_M | 34.14GB |
| Nous-Hermes-2-MoE-2x34B.Q4_1.gguf | Q4_1 | 35.49GB |
| Nous-Hermes-2-MoE-2x34B.Q5_0.gguf | Q5_0 | 39.0GB |
| Nous-Hermes-2-MoE-2x34B.Q5_K_S.gguf | Q5_K_S | 39.0GB |
| Nous-Hermes-2-MoE-2x34B.Q5_K.gguf | Q5_K | 40.12GB |
| Nous-Hermes-2-MoE-2x34B.Q5_K_M.gguf | Q5_K_M | 40.12GB |
| Nous-Hermes-2-MoE-2x34B.Q5_1.gguf | Q5_1 | 42.51GB |
| Nous-Hermes-2-MoE-2x34B.Q6_K.gguf | Q6_K | 17.31GB |
| Nous-Hermes-2-MoE-2x34B.Q8_0.gguf | Q8_0 | 60.18GB |
license: apache-2.0 model-index:
This is an experimental model to make an MoE of Nous Hermes 2 Yi 34B as Mixture of Expert.
The base model is Yi-34B.
All credits belong to NousResearch for fine tuned Yi model, 01-AI for Yi model, and Charles O. Goddard for the 'mergekit'.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 73.30 |
| AI2 Reasoning Challenge (25-Shot) | 66.64 |
| HellaSwag (10-Shot) | 85.73 |
| MMLU (5-Shot) | 76.49 |
| TruthfulQA (0-shot) | 58.08 |
| Winogrande (5-shot) | 83.35 |
| GSM8k (5-shot) | 69.52 |