107 lines
4.1 KiB
Markdown
107 lines
4.1 KiB
Markdown
---
|
||
base_model: stabilityai/stablelm-zephyr-3b
|
||
datasets:
|
||
- HuggingFaceH4/ultrachat_200k
|
||
- HuggingFaceH4/ultrafeedback_binarized
|
||
- meta-math/MetaMathQA
|
||
- WizardLM/WizardLM_evol_instruct_V2_196k
|
||
- Intel/orca_dpo_pairs
|
||
license: other
|
||
license_link: https://huggingface.co/stabilityai/stablelm-zephyr-3b/blob/main/LICENSE
|
||
language:
|
||
- en
|
||
model_creator: stabilityai
|
||
model_name: stablelm-zephyr-3b
|
||
model_type: stablelm_epoch
|
||
inference: false
|
||
tags:
|
||
- causal-lm
|
||
- stablelm_epoch
|
||
pipeline_tag: text-generation
|
||
prompt_template: |
|
||
<|system|>
|
||
{{system_message}}<|endoftext|>
|
||
<|user|>
|
||
{{prompt}}<|endoftext|>
|
||
<|assistant|>
|
||
|
||
quantized_by: brittlewis12
|
||
---
|
||
|
||
# StableLM Zephyr 3B GGUF
|
||
|
||
Original model: [StableLM Zephyr 3B](https://huggingface.co/stabilityai/stablelm-zephyr-3b)
|
||
Model creator: [Stability AI](https://huggingface.co/stabilityai)
|
||
|
||
This repo contains GGUF format model files for Stability AI’s StableLM Zephyr 3B.
|
||
|
||
> StableLM Zephyr 3B is a 3 billion parameter instruction tuned inspired by [HugginFaceH4's Zephyr 7B](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) training pipeline this model was trained on a mix of publicly available datasets, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290), evaluation for this model based on [MT Bench](https://tatsu-lab.github.io/alpaca_eval/) and [Alpaca Benchmark](https://tatsu-lab.github.io/alpaca_eval/).
|
||
|
||
|
||
### What is GGUF?
|
||
|
||
GGUF is a file format for representing AI models. It is the third version of the format, introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
|
||
Converted using llama.cpp b1960 ([26d6076](https://github.com/ggerganov/llama.cpp/commits/26d607608d794efa56df3bdb6043a2f94c1d632c))
|
||
|
||
### Prompt template: Zephyr
|
||
|
||
```
|
||
<|system|>
|
||
{{system_message}}<|endoftext|>
|
||
<|user|>
|
||
{{prompt}}<|endoftext|>
|
||
<|assistant|>
|
||
```
|
||
|
||
---
|
||
|
||
## Download & run with [cnvrs](https://twitter.com/cnvrsai) on iPhone, iPad, and Mac!
|
||
|
||
|
||
|
||
[cnvrs](https://testflight.apple.com/join/sFWReS7K) is the best app for private, local AI on your device:
|
||
- create & save **Characters** with custom system prompts & temperature settings
|
||
- download and experiment with any **GGUF model** you can [find on HuggingFace](https://huggingface.co/models?library=gguf)!
|
||
- make it your own with custom **Theme colors**
|
||
- powered by Metal ⚡️ & [Llama.cpp](https://github.com/ggerganov/llama.cpp), with **haptics** during response streaming!
|
||
- **try it out** yourself today, on [Testflight](https://testflight.apple.com/join/sFWReS7K)!
|
||
- follow [cnvrs on twitter](https://twitter.com/cnvrsai) to stay up to date
|
||
|
||
---
|
||
|
||
## Original Model Evaluations:
|
||
|
||
|
||
|
||
| Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
|
||
|-------------|-----|----|---------------|--------------|
|
||
| **StableLM Zephyr 3B** 🪁 | 3B | DPO | 6.64 | 76.00 |
|
||
| StableLM Zephyr (SFT only) | 3B | SFT | 6.04 | 71.15 |
|
||
| Capybara v1.9 | 3B | dSFT | 5.94 | - |
|
||
| MPT-Chat | 7B |dSFT |5.42| -|
|
||
| Xwin-LM v0.1 | 7B| dPPO| 6.19| 87.83|
|
||
| Mistral-Instruct v0.1 | 7B| - | 6.84 |-|
|
||
| Zephyr-7b-α |7B| dDPO| 6.88| -|
|
||
| Zephyr-7b-β| 7B | dDPO | 7.34 | 90.60 |
|
||
| Falcon-Instruct | 40B |dSFT |5.17 |45.71|
|
||
| Guanaco | 65B | SFT |6.41| 71.80|
|
||
| Llama2-Chat | 70B |RLHF |6.86| 92.66|
|
||
| Vicuna v1.3 | 33B |dSFT |7.12 |88.99|
|
||
| WizardLM v1.0 | 70B |dSFT |7.71 |-|
|
||
| Xwin-LM v0.1 | 70B |dPPO |- |95.57|
|
||
| GPT-3.5-turbo | - |RLHF |7.94 |89.37|
|
||
| Claude 2 | - |RLHF |8.06| 91.36|
|
||
| GPT-4 | -| RLHF |8.99| 95.28|
|
||
|
||
| Task | Value |
|
||
|-----------------------|---------------------------|
|
||
| ARC (25-shot) | 47.0 |
|
||
| HellaSwag (10-shot) | 74.2 |
|
||
| MMLU (5-shot) | 46.3 |
|
||
| TruthfulQA (0-shot) | 46.5 |
|
||
| Winogrande (5-shot) | 65.5 |
|
||
| GSM8K (5-shot) | 42.3 |
|
||
| BigBench (Avg) | 35.26 |
|
||
| AGI Benchmark (Avg) | 33.23 |
|
||
|