Downloads · 30 days
15.2K
85% of all-time downloads
RichardErkhov/Undi95_-_Emerhyst-20B-gguf
Undi95_-_Emerhyst-20B-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
15.2K
85% of all-time downloads
All-time downloads
18K
Public
Repo size
11.4 GB
Likes
1
Public
Click a slice to open those files.
.gguf11.4 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Emerhyst-20B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Emerhyst-20B.Q2_K.gguf | Q2_K | 6.91GB |
| Emerhyst-20B.IQ3_XS.gguf | IQ3_XS | 3.01GB |
| Emerhyst-20B.IQ3_S.gguf | IQ3_S | 0.38GB |
| Emerhyst-20B.Q3_K_S.gguf | Q3_K_S | 0.28GB |
| Emerhyst-20B.IQ3_M.gguf | IQ3_M | 0.01GB |
| Emerhyst-20B.Q3_K.gguf | Q3_K | 0.0GB |
| Emerhyst-20B.Q3_K_M.gguf | Q3_K_M | 0.0GB |
| Emerhyst-20B.Q3_K_L.gguf | Q3_K_L | 0.0GB |
| Emerhyst-20B.IQ4_XS.gguf | IQ4_XS | 0.0GB |
| Emerhyst-20B.Q4_0.gguf | Q4_0 | 0.0GB |
| Emerhyst-20B.IQ4_NL.gguf | IQ4_NL | 0.0GB |
| Emerhyst-20B.Q4_K_S.gguf | Q4_K_S | 0.0GB |
| Emerhyst-20B.Q4_K.gguf | Q4_K | 0.0GB |
| Emerhyst-20B.Q4_K_M.gguf | Q4_K_M | 0.0GB |
| Emerhyst-20B.Q4_1.gguf | Q4_1 | 0.0GB |
| Emerhyst-20B.Q5_0.gguf | Q5_0 | 0.0GB |
| Emerhyst-20B.Q5_K_S.gguf | Q5_K_S | 0.0GB |
| Emerhyst-20B.Q5_K.gguf | Q5_K | 0.0GB |
| Emerhyst-20B.Q5_K_M.gguf | Q5_K_M | 0.0GB |
| Emerhyst-20B.Q5_1.gguf | Q5_1 | 0.0GB |
| Emerhyst-20B.Q6_K.gguf | Q6_K | 0.0GB |
| Emerhyst-20B.Q8_0.gguf | Q8_0 | 0.0GB |
license: cc-by-nc-4.0 tags:

Merge of Amethyst 13B and Emerald 13B.
In addition, LimaRP v3 was used, is it recommanded to read the documentation.
<!-- description start -->This repo contains fp16 files of Emerhyst-20B.
<!-- description end --> <!-- description start -->Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:

You can follow these instruction format settings in SillyTavern. Replace tiny with your desired response length:

Special thanks to Sushi.
If you want to support me, you can here.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 51.85 |
| ARC (25-shot) | 61.69 |
| HellaSwag (10-shot) | 84.98 |
| MMLU (5-shot) | 56.98 |
| TruthfulQA (0-shot) | 54.16 |
| Winogrande (5-shot) | 76.09 |
| GSM8K (5-shot) | 8.49 |
| DROP (3-shot) | 20.56 |