HERMES
Safetensors
English
qwen2
ai-evaluation
mathematics
chain-of-thought
hermes-format
post-trained
anti-hallucination
Instructions to use ray0rf1re/hyper-Nix.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- HERMES
How to use ray0rf1re/hyper-Nix.2 with HERMES:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Delete README.md
Browse files
README.md
DELETED
|
@@ -1,56 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
datasets:
|
| 3 |
-
- ray0rf1re/FineWeb-Nano
|
| 4 |
-
- Nix-ai/Cat-v2.8
|
| 5 |
-
- databricks/databricks-dolly-15k
|
| 6 |
-
- allenai/ai2_arc
|
| 7 |
-
- lighteval/MATH-Hard
|
| 8 |
-
- tatsu-lab/alpaca
|
| 9 |
-
- HuggingFaceTB/smoltalk
|
| 10 |
-
- openai/gsm8k
|
| 11 |
-
language:
|
| 12 |
-
- en
|
| 13 |
-
license: other
|
| 14 |
-
license_name: hyper-v2
|
| 15 |
-
---
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
๐ Hyper-Nix.2
|
| 19 |
-
|
| 20 |
-
Welcome to the official repository for Hyper-Nix.2!
|
| 21 |
-
|
| 22 |
-
Note: This model is currently in the final stages of training. The uploaded weights represent an almost-fully trained checkpoint, and the final version will be updated soon.
|
| 23 |
-
|
| 24 |
-
๐ Model Details
|
| 25 |
-
|
| 26 |
-
Creator: ray0rf1re
|
| 27 |
-
|
| 28 |
-
Old Version: ray0rf1re/hyper-nix.1
|
| 29 |
-
|
| 30 |
-
Model Type: Causal Language Model (Text Generation)
|
| 31 |
-
|
| 32 |
-
Language(s): English
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
๐ Model Description
|
| 36 |
-
|
| 37 |
-
Hyper-Nix.2 is a text-generation model designed for a variety of tasks including conversation, mathematical reasoning, question answering, and instruction following. It builds upon the foundation of hyper-nix.1 with a much more diverse and high-quality dataset mixture. The goal of this model is to provide helpful, smart, and logical responses for a wide range of use cases.
|
| 38 |
-
|
| 39 |
-
๐ Training Data
|
| 40 |
-
|
| 41 |
-
To make Hyper-Nix.2 smart and versatile, it was trained on a blend of datasets covering math, logic, roleplay, and general knowledge.
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
Format
|
| 45 |
-
|
| 46 |
-
Est. Size
|
| 47 |
-
0.1b peramiters 101.3m
|
| 48 |
-
|
| 49 |
-
๐ป Intended Use
|
| 50 |
-
|
| 51 |
-
This model is intended for:
|
| 52 |
-
|
| 53 |
-
evualation of other ais (once post training is compleated)
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
License: Hyper-Nix Restricted Open License (HROL-v2)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|