---
license: llama2
language:
  - en
tags:
  - mistral
  - merge
library_name: transformers
pipeline_tag: text-generation
base_model:
  - Weyaxi/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp
  - uukuguy/speechless-mistral-six-in-one-7b
datasets:
  - stingning/ultrachat
  - garage-bAInd/Open-Platypus
  - Open-Orca/OpenOrca
  - TIGER-Lab/MathInstruct
  - OpenAssistant/oasst_top1_2023-08-25
  - teknium/openhermes
  - meta-math/MetaMathQA
  - Open-Orca/SlimOrca

---

<p align="center">
  <img src="https://codeberg.org/aninokuma/DeydooAssistant/raw/branch/main/logo.webp" height="256px" alt="SynthIQ">
</p>

# SynthIQ

This is SynthIQ, rated **92.23/100** by GPT-4 across varied complex prompts. I used [mergekit](https://github.com/cg123/mergekit) to merge models.

| Benchmark Name   | Score |
| ---------------- | ----- |
| ARC              | 65.87 |
| HellaSwag        | 85.82 |
| MMLU             | 64.75 |
| TruthfulQA       | 57.00 |
| Winogrande       | 78.69 |
| GSM8K            | 64.06 |
| AGIEval          | 42.67 |
| GPT4All          | 73.71 |
| Bigbench         | 44.59 |


## Update - 19/01/2024
Tested to work well with autogen and CrewAI

GGUF Files

[Q4_K_M](https://huggingface.co/sethuiyer/SynthIQ_GGUF/blob/main/synthiq.Q4_K_M.gguf) - medium, balanced quality - recommended

[Q_6_K](https://huggingface.co/sethuiyer/SynthIQ_GGUF/blob/main/synthiq.Q6_K.gguf) - very large, extremely low quality loss

[Q8_0](https://huggingface.co/sethuiyer/SynthIQ_GGUF/blob/main/synthiq.Q8.gguf) - very large, extremely low quality loss - not recommended

**Important Update**: SynthIQ is now available on Ollama. You can use it by running the command ```ollama run stuehieyr/synthiq``` in your 
terminal. If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on 
a Google Colab backend.


# Yaml Config

```yaml

slices:
  - sources:
      - model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-openchat-3.5-1210-Slerp
        layer_range: [0, 32]
      - model: uukuguy/speechless-mistral-six-in-one-7b
        layer_range: [0, 32]

merge_method: slerp
base_model: mistralai/Mistral-7B-v0.1

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 # fallback for rest of tensors
tokenizer_source: union

dtype: bfloat16

```

<!-- prompt-template start -->
## Prompt template: ChatML

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

```

<!-- prompt-template end -->


License is LLama2 license as uukuguy/speechless-mistral-six-in-one-7b is llama2 license.

# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_sethuiyer__SynthIQ-7b)

# [Nous Benchmark Evalation Results](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard)
Detailed results can be found [here](https://gist.github.com/sethuiyer/f47dee388a4e95d46181c98d37d66a58)