Downloads · 30 days
130
5% of all-time downloads
RichardErkhov/jan-hq_-_Phoenix-v1-8x7B-gguf
jan-hq_-_Phoenix-v1-8x7B-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
130
5% of all-time downloads
All-time downloads
2.4K
Public
Repo size
555 GB
Likes
0
Public
Click a slice to open those files.
.gguf611 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Phoenix-v1-8x7B - GGUF
| Name | Quant method | Size |
|---|---|---|
| Phoenix-v1-8x7B.Q2_K.gguf | Q2_K | 16.12GB |
| Phoenix-v1-8x7B.IQ3_XS.gguf | IQ3_XS | 18.02GB |
| Phoenix-v1-8x7B.IQ3_S.gguf | IQ3_S | 19.03GB |
| Phoenix-v1-8x7B.Q3_K_S.gguf | Q3_K_S | 19.03GB |
| Phoenix-v1-8x7B.IQ3_M.gguf | IQ3_M | 19.96GB |
| Phoenix-v1-8x7B.Q3_K.gguf | Q3_K | 21.0GB |
| Phoenix-v1-8x7B.Q3_K_M.gguf | Q3_K_M | 21.0GB |
| Phoenix-v1-8x7B.Q3_K_L.gguf | Q3_K_L | 22.51GB |
| Phoenix-v1-8x7B.IQ4_XS.gguf | IQ4_XS | 23.63GB |
| Phoenix-v1-8x7B.Q4_0.gguf | Q4_0 | 24.63GB |
| Phoenix-v1-8x7B.IQ4_NL.gguf | IQ4_NL | 24.91GB |
| Phoenix-v1-8x7B.Q4_K_S.gguf | Q4_K_S | 24.91GB |
| Phoenix-v1-8x7B.Q4_K.gguf | Q4_K | 23.65GB |
| Phoenix-v1-8x7B.Q4_K_M.gguf | Q4_K_M | 26.49GB |
| Phoenix-v1-8x7B.Q4_1.gguf | Q4_1 | 27.32GB |
| Phoenix-v1-8x7B.Q5_0.gguf | Q5_0 | 30.02GB |
| Phoenix-v1-8x7B.Q5_K_S.gguf | Q5_K_S | 30.02GB |
| Phoenix-v1-8x7B.Q5_K.gguf | Q5_K | 30.95GB |
| Phoenix-v1-8x7B.Q5_K_M.gguf | Q5_K_M | 30.95GB |
| Phoenix-v1-8x7B.Q5_1.gguf | Q5_1 | 32.71GB |
| Phoenix-v1-8x7B.Q6_K.gguf | Q6_K | 35.74GB |
| Phoenix-v1-8x7B.Q8_0.gguf | Q8_0 | 46.22GB |
license: apache-2.0 language:
This is a highly experimental model for merging models into a MOE model.
Special thanks to the interested work of Chargoddard and Undi95
Updating
You can run this model using Jan Desktop on Mac, Windows, or Linux.
Jan is an open source, ChatGPT alternative that is:
1337 with OpenAI compatible endpoints
Jan believes in the need for an open-source AI ecosystem and is building the infra and tooling to allow open-source AIs to compete on a level playing field with proprietary ones.
Jan's long-term vision is to build a cognitive framework for future robots, who are practical, useful assistants for humans and businesses in everyday life.
This is a test project for merging models.
Detailed results can be found here.
| Metric | Value |
|---|---|
| Avg. | ? |
| ARC (25-shot) | ? |
| HellaSwag (10-shot) | ? |
| MMLU (5-shot) | ? |
| TruthfulQA (0-shot) | ? |
| Winogrande (5-shot) | ? |
| GSM8K (5-shot) | ? |