Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,63 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- stepfun-ai/Step-3.5-Flash-SFT
|
| 5 |
+
language:
|
| 6 |
+
- aa
|
| 7 |
+
metrics:
|
| 8 |
+
- character
|
| 9 |
+
base_model:
|
| 10 |
+
- HahahucCS/Qwen3.5-35B-A3B-Uncensored-HahahucCS-Aggressive
|
| 11 |
+
pipeline_tag: text-generation
|
| 12 |
+
tags:
|
| 13 |
+
- agent
|
| 14 |
+
- ai
|
| 15 |
+
- chatbot
|
| 16 |
+
- uncensored
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# 🔥 BXFVC AI Model
|
| 20 |
+
|
| 21 |
+
## 🚀 Overview
|
| 22 |
+
BXFVC is a powerful AI model built on top of Qwen 3.5 35B, designed for fast, creative, and flexible text generation.
|
| 23 |
+
|
| 24 |
+
It works best for:
|
| 25 |
+
- 💬 Chat conversations
|
| 26 |
+
- 🧠 Creative writing
|
| 27 |
+
- 🎮 Roleplay
|
| 28 |
+
- ⚡ Fast responses
|
| 29 |
+
|
| 30 |
+
---
|
| 31 |
+
|
| 32 |
+
## 🧠 Features
|
| 33 |
+
- Uncensored-style responses
|
| 34 |
+
- Strong personality output
|
| 35 |
+
- Creative storytelling
|
| 36 |
+
- Good dialogue generation
|
| 37 |
+
|
| 38 |
+
---
|
| 39 |
+
|
| 40 |
+
## ⚠️ Limitations
|
| 41 |
+
- May produce incorrect info
|
| 42 |
+
- Can be aggressive or unfiltered
|
| 43 |
+
- Not safe for all audiences
|
| 44 |
+
- No built-in moderation
|
| 45 |
+
|
| 46 |
+
---
|
| 47 |
+
|
| 48 |
+
## 🛠️ Usage (Python)
|
| 49 |
+
|
| 50 |
+
```python
|
| 51 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 52 |
+
|
| 53 |
+
model_name = "your-username/bxfvc" # CHANGE THIS
|
| 54 |
+
|
| 55 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 56 |
+
model = AutoModelForCausalLM.from_pretrained(model_name)
|
| 57 |
+
|
| 58 |
+
prompt = "Write a futuristic story about AI taking over."
|
| 59 |
+
|
| 60 |
+
inputs = tokenizer(prompt, return_tensors="pt")
|
| 61 |
+
outputs = model.generate(**inputs, max_new_tokens=200)
|
| 62 |
+
|
| 63 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|