94 lines
3.3 KiB
Markdown
94 lines
3.3 KiB
Markdown
---
|
||
base_model: h2oai/h2o-danube-1.8b-chat
|
||
datasets:
|
||
- HuggingFaceH4/ultrafeedback_binarized
|
||
- Intel/orca_dpo_pairs
|
||
- argilla/distilabel-math-preference-dpo
|
||
- Open-Orca/OpenOrca
|
||
- OpenAssistant/oasst2
|
||
- HuggingFaceH4/ultrachat_200k
|
||
- meta-math/MetaMathQA
|
||
license: apache-2.0
|
||
language:
|
||
- en
|
||
model_creator: h2oai
|
||
model_name: h2o-danube-1.8b-chat
|
||
model_type: mistral
|
||
inference: false
|
||
tags:
|
||
- gpt
|
||
- llm
|
||
- large language model
|
||
- h2o-llmstudio
|
||
pipeline_tag: text-generation
|
||
prompt_template: |
|
||
<|system|>{{system_message}}</s>
|
||
<|prompt|>{{prompt}}</s>
|
||
<|answer|>
|
||
|
||
quantized_by: brittlewis12
|
||
---
|
||
|
||
# h2o-danube-1.8b-chat GGUF
|
||
|
||
|
||
Original model: [h2o-danube-1.8b-chat](https://huggingface.co/h2oai/h2o-danube-1.8b-chat)
|
||
Model creator: [h2oai](https://huggingface.co/h2oai)
|
||
|
||
This repo contains GGUF format model files for h2oai’s h2o-danube-1.8b-chat.
|
||
|
||
> h2o-danube-1.8b-chat is an chat fine-tuned model by H2O.ai with 1.8 billion parameters. For details, please refer to our [Technical Report](https://arxiv.org/abs/2401.16818). We release three versions of this model:
|
||
>
|
||
> - h2oai/h2o-danube-1.8b-base Base model
|
||
> - h2oai/h2o-danube-1.8b-sft SFT tuned
|
||
> - h2oai/h2o-danube-1.8b-chat SFT + DPO tuned
|
||
|
||
> We adjust the Llama 2 architecture for a total of around 1.8b parameters. We use the original Llama 2 tokenizer with a vocabulary size of 32,000 and train our model up to a context length of 16,384. We incorporate the sliding window attention from mistral with a size of 4,096.
|
||
|
||
Refer to h2o.ai’s model [disclaimer](https://huggingface.co/h2oai/h2o-danube-1.8b-chat/blob/main/README.md#disclaimer) for terms of use.
|
||
|
||
|
||
### 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 b2037 ([1cfb537](https://github.com/ggerganov/llama.cpp/commits/1cfb5372cf5707c8ec6dde7c874f4a44a6c4c915))
|
||
|
||
### Prompt template:
|
||
|
||
```
|
||
<|system|>{{system_message}}</s>
|
||
<|prompt|>{{prompt}}</s>
|
||
<|answer|>
|
||
```
|
||
|
||
---
|
||
|
||
## 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:
|
||
|
||
> Commonsense, world-knowledge and reading comprehension tested in 0-shot:
|
||
|
||
| Benchmark | acc_n |
|
||
|:--------------|:--------:|
|
||
| ARC-easy | 67.51 |
|
||
| ARC-challenge | 39.25 |
|
||
| BoolQ | 77.89 |
|
||
| Hellaswag | 67.60 |
|
||
| OpenBookQA | 39.20 |
|
||
| PiQA | 76.71 |
|
||
| TriviaQA | 36.29 |
|
||
| Winogrande | 65.35 |
|