Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
inference: false
|
| 7 |
+
tags:
|
| 8 |
+
- transformers
|
| 9 |
+
- gguf
|
| 10 |
+
- imatrix
|
| 11 |
+
- Borealis-10.7B-DPO
|
| 12 |
+
---
|
| 13 |
+
Quantizations of https://huggingface.co/Undi95/Borealis-10.7B-DPO
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
### Inference Clients/UIs
|
| 17 |
+
* [llama.cpp](https://github.com/ggerganov/llama.cpp)
|
| 18 |
+
* [KoboldCPP](https://github.com/LostRuins/koboldcpp)
|
| 19 |
+
* [ollama](https://github.com/ollama/ollama)
|
| 20 |
+
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
|
| 21 |
+
* [GPT4All](https://github.com/nomic-ai/gpt4all)
|
| 22 |
+
* [jan](https://github.com/janhq/jan)
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
# From original readme
|
| 26 |
+
|
| 27 |
+
## Borealis
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
Borealis-10.7B-DPO is a 10.7B model made of 48 Mistral 7B layers, finetuned for +70h on 2xA6000 on a big RP and Conversational dataset with llama2 configuration of Axolotl, like SOLAR.
|
| 32 |
+
|
| 33 |
+
This variant had a DPO train on top of it.
|
| 34 |
+
|
| 35 |
+
<!-- description start -->
|
| 36 |
+
## Description
|
| 37 |
+
|
| 38 |
+
This repo contains fp16 files of Borealis-10.7B-DPO, a conversational model.
|
| 39 |
+
|
| 40 |
+
The goal of this model isn't to break all benchmark, but to have a better RP/ERP/Conversational model.
|
| 41 |
+
|
| 42 |
+
It was trained on multiple basic dataset to make it intelligent, but majority of the dataset was basic conversations.
|
| 43 |
+
|
| 44 |
+
<!-- description end -->
|
| 45 |
+
<!-- description start -->
|
| 46 |
+
## Dataset used
|
| 47 |
+
|
| 48 |
+
- NobodyExistsOnTheInternet/ToxicQAFinal
|
| 49 |
+
- teknium/openhermes
|
| 50 |
+
- unalignment/spicy-3.1
|
| 51 |
+
- Doctor-Shotgun/no-robots-sharegpt
|
| 52 |
+
- Undi95/toxic-dpo-v0.1-sharegpt
|
| 53 |
+
- Aesir [1], [2], [3-SFW], [3-NSFW]
|
| 54 |
+
- lemonilia/LimaRP
|
| 55 |
+
- Squish42/bluemoon-fandom-1-1-rp-cleaned
|
| 56 |
+
- Undi95/ConversationChronicles-sharegpt-SHARDED (2 sets, modified)
|
| 57 |
+
|
| 58 |
+
## DPO Dataset used
|
| 59 |
+
|
| 60 |
+
- Intel/orca_dpo_pairs
|
| 61 |
+
- NobodyExistsOnTheInternet/ToxicDPOqa
|
| 62 |
+
- Undi95/toxic-dpo-v0.1-NoWarning
|
| 63 |
+
|
| 64 |
+
<!-- description end -->
|
| 65 |
+
<!-- prompt-template start -->
|
| 66 |
+
## Prompt format: NsChatml
|
| 67 |
+
```
|
| 68 |
+
<|im_system|>
|
| 69 |
+
{sysprompt}<|im_end|>
|
| 70 |
+
<|im_user|>
|
| 71 |
+
{input}<|im_end|>
|
| 72 |
+
<|im_bot|>
|
| 73 |
+
{output}<|im_end|>
|
| 74 |
+
```
|