Edit model card

image/png

Attempt to recreate Amethyst-13B but in 20B. The two model was glued together with a sparkle of Unholy.

In addition, LimaRP v3 was used, is it recommanded to read the documentation.

Description

This repo contains fp16 files of Amethyst-20B.

Models and loras used

  • Xwin-LM/Xwin-LM-13B-V0.1
  • The-Face-Of-Goonery/Huginn-13b-FP16
  • zattio770/120-Days-of-LORA-v2-13B
  • lemonilia/LimaRP-Llama2-13B-v3-EXPERIMENT
  • Undi95/Unholy-v1-12L-13B

Prompt template: Alpaca

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

LimaRP v3 usage and suggested settings

image/png

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

image/png

Special thanks to Sushi.

If you want to support me, you can here.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 50.38
ARC (25-shot) 62.2
HellaSwag (10-shot) 83.11
MMLU (5-shot) 55.88
TruthfulQA (0-shot) 53.2
Winogrande (5-shot) 74.19
GSM8K (5-shot) 5.31
DROP (3-shot) 18.75
Downloads last month
1,666
Safetensors
Model size
20B params
Tensor type
F32
·
BF16
·
Inference API
Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated) instead.

Collection including Undi95/U-Amethyst-20B