|
--- |
|
base_model: mlabonne/NeuralDaredevil-7B |
|
inference: false |
|
language: |
|
- en |
|
license: apache-2.0 |
|
model_creator: mlabonne |
|
model_name: NeuralDaredevil-7B |
|
model_type: mistral |
|
datasets: |
|
- argilla/distilabel-intel-orca-dpo-pairs |
|
pipeline_tag: text-generation |
|
prompt_template: "<|system|> |
|
|
|
</s> |
|
|
|
<|user|> |
|
|
|
{prompt}</s> |
|
|
|
<|assistant|> |
|
|
|
" |
|
quantized_by: brittlewis12 |
|
--- |
|
|
|
# NeuralDaredevil-7B GGUF |
|
|
|
Original model: [NeuralDaredevil-7B](https://huggingface.co/mlabonne/NeuralDaredevil-7B) |
|
Model creator: [Maxime Labonne](https://huggingface.co/mlabonne) |
|
|
|
This repo contains GGUF format model files for Maxime Labonne’s NeuralDaredevil-7B. |
|
|
|
Maxime discussing NeuralDaredevil on [Twitter](https://twitter.com/maximelabonne/status/1746979986370666741): |
|
> 🤝 NeuralDaredevil is actually trained using [argilla’s] excellent distilled version of the [orca-dpo-pairs](https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs) made with [distilabel](https://github.com/argilla-io/distilabel). |
|
|
|
|
|
### 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 build 1879 (revision [3e5ca79](https://github.com/ggerganov/llama.cpp/commit/3e5ca7931c68152e4ec18d126e9c832dd84914c8)) |
|
|
|
### Prompt template: Zephyr |
|
|
|
Zephyr-style appears to work well! |
|
|
|
``` |
|
<|system|> |
|
{{system_message}}</s> |
|
<|user|> |
|
{{prompt}}</s> |
|
<|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: |
|
|
|
Evaluations reported from mlabonne’s alternative leaderboard, YALL: [Yet_Another_LLM_Leaderboard](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard). |
|
|
|
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average| |
|
|-------------------------------------------------------------------------|------:|------:|---------:|-------:|------:| |
|
|[**NeuralDaredevil-7B**](https://huggingface.co/mlabonne/NeuralDaredevil-7B) | **45.23**| **76.2**| **67.61**| **48.52**| **59.39**| |
|
|[Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) | 38.5 | 71.64 | 66.82 | 42.29 | 54.81 | |
|
|[openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106) | 44.17 | 73.72 | 52.53 | 44.4 | 53.71 | |
|
|[OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) | 42.75 | 72.99 | 52.99 | 40.94 | 52.42 | |
|
|
