You can deploy this model and start earning money today!

RichardErkhov/
jan-ai_-_Solar-10.7B-SLERP-gguf

Name: jan-ai_-_Solar-10.7B-SLERP-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Solar-10.7B-SLERP - GGUF

Model creator: https://huggingface.co/jan-ai/
Original model: https://huggingface.co/jan-ai/Solar-10.7B-SLERP/

Name	Quant method	Size
Solar-10.7B-SLERP.Q2_K.gguf	Q2_K	3.73GB
Solar-10.7B-SLERP.IQ3_XS.gguf	IQ3_XS	4.14GB
Solar-10.7B-SLERP.IQ3_S.gguf	IQ3_S	4.37GB
Solar-10.7B-SLERP.Q3_K_S.gguf	Q3_K_S	4.34GB
Solar-10.7B-SLERP.IQ3_M.gguf	IQ3_M	4.51GB
Solar-10.7B-SLERP.Q3_K.gguf	Q3_K	4.84GB
Solar-10.7B-SLERP.Q3_K_M.gguf	Q3_K_M	4.84GB
Solar-10.7B-SLERP.Q3_K_L.gguf	Q3_K_L	5.26GB
Solar-10.7B-SLERP.IQ4_XS.gguf	IQ4_XS	5.43GB
Solar-10.7B-SLERP.Q4_0.gguf	Q4_0	5.66GB
Solar-10.7B-SLERP.IQ4_NL.gguf	IQ4_NL	5.72GB
Solar-10.7B-SLERP.Q4_K_S.gguf	Q4_K_S	5.7GB
Solar-10.7B-SLERP.Q4_K.gguf	Q4_K	6.02GB
Solar-10.7B-SLERP.Q4_K_M.gguf	Q4_K_M	6.02GB
Solar-10.7B-SLERP.Q4_1.gguf	Q4_1	6.27GB
Solar-10.7B-SLERP.Q5_0.gguf	Q5_0	6.89GB
Solar-10.7B-SLERP.Q5_K_S.gguf	Q5_K_S	6.89GB
Solar-10.7B-SLERP.Q5_K.gguf	Q5_K	7.08GB
Solar-10.7B-SLERP.Q5_K_M.gguf	Q5_K_M	7.08GB
Solar-10.7B-SLERP.Q5_1.gguf	Q5_1	7.51GB
Solar-10.7B-SLERP.Q6_K.gguf	Q6_K	8.2GB
Solar-10.7B-SLERP.Q8_0.gguf	Q8_0	10.62GB

Original model description:

license: apache-2.0 language:

WARNING

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

Model: Solar-10.7B-SLERP
GGUF: Solar-10.7B-SLERP-GGUF

Jan - Discord

Model Description

This model uses the Slerp merge method from the best models on 14th Dec on the OpenLLM Leaderboard:

base model: upstage/SOLAR-10.7B-Instruct-v1.0

The yaml config file for this model is here:

yaml

slices:
  - sources:
      - model: upstage/SOLAR-10.7B-Instruct-v1.0
        layer_range: [0, 48]
      - model: janhq/Pandora-v1-10.7B
        layer_range: [0, 48]
merge_method: slerp
base_model: upstage/SOLAR-10.7B-Instruct-v1.0
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
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 Solar-10.7B-SLERP-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_-_Solar-10.7B-SLERP-gguf