Quantization made by Richard Erkhov.

Pandora-13B-v1 - GGUF

Model creator: https://huggingface.co/jan-ai/
Original model: https://huggingface.co/jan-ai/Pandora-13B-v1/

Name	Quant method	Size
Pandora-13B-v1.Q2_K.gguf	Q2_K	4.33GB
Pandora-13B-v1.IQ3_XS.gguf	IQ3_XS	4.81GB
Pandora-13B-v1.IQ3_S.gguf	IQ3_S	5.07GB
Pandora-13B-v1.Q3_K_S.gguf	Q3_K_S	5.04GB
Pandora-13B-v1.IQ3_M.gguf	IQ3_M	5.24GB
Pandora-13B-v1.Q3_K.gguf	Q3_K	5.62GB
Pandora-13B-v1.Q3_K_M.gguf	Q3_K_M	5.62GB
Pandora-13B-v1.Q3_K_L.gguf	Q3_K_L	6.11GB
Pandora-13B-v1.IQ4_XS.gguf	IQ4_XS	6.3GB
Pandora-13B-v1.Q4_0.gguf	Q4_0	6.57GB
Pandora-13B-v1.IQ4_NL.gguf	IQ4_NL	6.64GB
Pandora-13B-v1.Q4_K_S.gguf	Q4_K_S	6.62GB
Pandora-13B-v1.Q4_K.gguf	Q4_K	6.99GB
Pandora-13B-v1.Q4_K_M.gguf	Q4_K_M	6.99GB
Pandora-13B-v1.Q4_1.gguf	Q4_1	7.29GB
Pandora-13B-v1.Q5_0.gguf	Q5_0	8.01GB
Pandora-13B-v1.Q5_K_S.gguf	Q5_K_S	8.01GB
Pandora-13B-v1.Q5_K.gguf	Q5_K	8.22GB
Pandora-13B-v1.Q5_K_M.gguf	Q5_K_M	8.22GB
Pandora-13B-v1.Q5_1.gguf	Q5_1	8.73GB
Pandora-13B-v1.Q6_K.gguf	Q6_K	9.53GB
Pandora-13B-v1.Q8_0.gguf	Q8_0	12.35GB

Original model description:

license: apache-2.0 language: - en

WARNING

This is a model file only for evaluation. Please use the model here:

Model: Pandora-v1-13B
GGUF: Pandora-v1-13B-GGUF

Jan - Discord

Model Description

This model uses the passthrough merge method from the best 7B models on the OpenLLM Leaderboard:

The yaml config file for this model is here:

slices:
  - sources:
    - model: "viethq188/LeoScorpius-7B-Chat-DPO"
      layer_range: [0, 24]
  - sources:
    - model: "GreenNode/GreenNodeLM-7B-v1olet"
      layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16

Prompt template

ChatML

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Run this model

You can run this model using Jan 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

Please use the Pandora-v1-13B-GGUF when using on Jan.

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)	?

RichardErkhov
/

jan-ai_-_Pandora-13B-v1-gguf