Quantizations of https://huggingface.co/yuuko-eth/Chihiro-7B-v0.1

Inference Clients/UIs


From original readme

This is an experimental Mistral-architecture SLERP merge with two brilliant base models. Zebrafish and Breeze were used together in this work.

Model configuration is as follows:

To use the model, please use either prompt templates suggested by the base models, or just slap the Mistral one on.



Benchmarks

Evaluation suite: OpenLLM

Model ARC HellaSwag MMLU TruthfulQA Winogrande GSM8K
Chihiro-7B-v0.1 68.52 85.95 (not yet evaluated) 63.81 81.77 64.22

Evaluation suite: Nous

Model AGIEval GPT4All TruthfulQA Bigbench Average
Chihiro-7B-v0.1 45.16 75.26 63.82 47.38 57.91

Average: 47.38%

Average score: 57.91%

Evaluated Apr. 27, 2024, NVIDIA RTX 4090



Downloads last month
522
GGUF
Model size
7.49B params
Architecture
llama

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model authors have turned it off explicitly.