Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
license: mit
|
| 5 |
+
tags:
|
| 6 |
+
- coding
|
| 7 |
+
- ui
|
| 8 |
+
- chat
|
| 9 |
+
- math
|
| 10 |
+
- factual
|
| 11 |
+
- agent
|
| 12 |
+
- multimodal
|
| 13 |
+
base_model:
|
| 14 |
+
- mistralai/Mixtral-8x7B-v0.1
|
| 15 |
+
- OpenBuddy/openbuddy-openllama-7b-v12-bf16
|
| 16 |
+
- HuggingFaceH4/mistral-7b-grok
|
| 17 |
+
- togethercomputer/RedPajama-INCITE-7B-Chat
|
| 18 |
+
datasets:
|
| 19 |
+
- hotboxxgenn/mix-openhermes-openorca-platypus-airoboros-chatalpaca-opencode
|
| 20 |
+
- microsoft/rStar-Coder
|
| 21 |
+
- ed001/ds-coder-instruct-v1
|
| 22 |
+
- bigcode/starcoderdata
|
| 23 |
+
- bigcode/starcoder2data-extras
|
| 24 |
+
- codeparrot/self-instruct-starcoder
|
| 25 |
+
- mrtoy/mobile-ui-design
|
| 26 |
+
- YashJain/UI-Elements-Detection-Dataset
|
| 27 |
+
- tecky-tech/Tecky-UI-Elements-VLM
|
| 28 |
+
- Tesslate/UIGEN-T2
|
| 29 |
+
- FineWeb
|
| 30 |
+
- OpenWebMath
|
| 31 |
+
- UltraChat
|
| 32 |
+
- WizardCoderData
|
| 33 |
+
library_name: transformers
|
| 34 |
+
---
|
| 35 |
+
|
| 36 |
+
# 🍓 BerryAI
|
| 37 |
+
|
| 38 |
+
**Author:** [@hotboxxgenn](https://huggingface.co/hotboxxgenn)
|
| 39 |
+
**Version:** 1.1
|
| 40 |
+
**Type:** Conversational + Coding + UI + Math + Factual Model
|
| 41 |
+
**Base:** Mixtral 8x7B, OpenBuddy, Mistral-Grok, RedPajama
|
| 42 |
+
|
| 43 |
+
---
|
| 44 |
+
|
| 45 |
+
## ✨ Overview
|
| 46 |
+
|
| 47 |
+
BerryAI is a **multi-skill LLM** designed to perform:
|
| 48 |
+
- 💻 **Coding** — Python, JS, React, Tailwind, multi-step reasoning
|
| 49 |
+
- 🎨 **UI generation** — generate clean, responsive interfaces
|
| 50 |
+
- 💬 **Conversational chat** — helpful, creative, engaging tone
|
| 51 |
+
- 🧮 **Math reasoning** — step-by-step calculations
|
| 52 |
+
- 🔍 **Factual grounding** — reduced hallucination, improved accuracy
|
| 53 |
+
|
| 54 |
+
---
|
| 55 |
+
|
| 56 |
+
## 🚀 Usage
|
| 57 |
+
|
| 58 |
+
```python
|
| 59 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 60 |
+
|
| 61 |
+
tokenizer = AutoTokenizer.from_pretrained("hotboxxgenn/BerryAI")
|
| 62 |
+
model = AutoModelForCausalLM.from_pretrained("hotboxxgenn/BerryAI")
|
| 63 |
+
|
| 64 |
+
prompt = "Generate a responsive React login form with Tailwind CSS."
|
| 65 |
+
inputs = tokenizer(prompt, return_tensors="pt")
|
| 66 |
+
outputs = model.generate(**inputs, max_new_tokens=200)
|
| 67 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|