|
--- |
|
license: mit |
|
language: |
|
- en |
|
metrics: |
|
- bleurt |
|
- bleu |
|
- chrf |
|
datasets: |
|
- Raiff1982/coredata |
|
- Raiff1982/pineco |
|
base_model: |
|
- tiiuae/falcon-40b |
|
- mistralai/Mistral-7B-v0.3 |
|
tags: |
|
- medical |
|
- code |
|
- text-generation |
|
- transformers |
|
pipeline_tag: text-generation |
|
library_name: transformers |
|
--- |
|
|
|
# Codette - Falcon & Mistral Merged Model |
|
|
|
## 🧠 Overview |
|
|
|
**Codette** is an advanced AI assistant designed to support users across cognitive, creative, and analytical tasks. |
|
This model merges **Falcon-40B** and **Mistral-7B** to deliver high performance in text generation, medical diagnostics, and code reasoning. |
|
|
|
--- |
|
|
|
## ⚡ Features |
|
|
|
- ✅ Merges Falcon-40B & Mistral-7B for enhanced capabilities |
|
- ✅ Supports multi-modal text generation, medical analysis, and code synthesis |
|
- ✅ Fine-tuned on domain-specific datasets (`Raiff1982/coredata`, `Raiff1982/pineco`) |
|
- ✅ Optimized for research, enterprise AI, and advanced reasoning |
|
|
|
--- |
|
|
|
## 📂 Model Details |
|
|
|
- **Base Models:** Falcon-40B, Mistral-7B-v0.3 |
|
- **Architecture:** Transformer-based language model |
|
- **Use Cases:** Text generation, code assistance, research, medical insights |
|
- **Training Datasets:** |
|
- `Raiff1982/coredata`: medical and reasoning-focused samples |
|
- `Raiff1982/pineco`: mixed domain creative + technical prompts |
|
|
|
--- |
|
|
|
## 📖 Usage |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model_name = "Raiff1982/Codette" |
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True) |
|
|
|
prompt = "How can AI improve medical diagnostics?" |
|
inputs = tokenizer(prompt, return_tensors="pt") |
|
output = model.generate(**inputs, max_length=200) |
|
print(tokenizer.decode(output[0], skip_special_tokens=True)) |
