You can deploy this model and start earning money today!

RichardErkhov/
jan-hq_-_Phoenix-v1-8x7B-gguf

Name: jan-hq_-_Phoenix-v1-8x7B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Phoenix-v1-8x7B - GGUF

Model creator: https://huggingface.co/jan-hq/
Original model: https://huggingface.co/jan-hq/Phoenix-v1-8x7B/

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

Original model description:

license: apache-2.0 language:

Jan - Discord

Model Description

This is a highly experimental model for merging models into a MOE model.

base model: trinity-v1
1. trinity-v1: for General Chat
2. Toppy-M-7B: for Role-playing
3. CodeLlama-7b-Instruct-hf: for Coding
4. Seraph-7B: for Writing

Special thanks to the interested work of Chargoddard and Undi95

Updating

Run this model

You can run this model using Jan Desktop on Mac, Windows, or Linux.

Jan is an open source, ChatGPT alternative that is:

💻 100% offline on your machine : Your conversations remain confidential, and visible only to you.
🗂️ An Open File Format: Conversations and model settings stay on your computer and can be exported or deleted at any time.
🌐 OpenAI Compatible: Local server on port 1337 with OpenAI compatible endpoints
🌍 Open Source & Free: We build in public; check out our Github

About Jan

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.

Jan Model Merger

This is a test project for merging models.

Open LLM Leaderboard Evaluation Results

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)	?

Acknowlegement

[mergekit] (https://github.com/cg123/mergekit)
DARE
lm-evaluation-harness

RichardErkhov/jan-hq_-_Phoenix-v1-8x7B-gguf