| Task | Dataset | % |
|---|---|---|
| 💬 Chat + General | OpenAssistant + UltraChat + Alpaca | 50% |
| 💻 Coding | CodeAlpaca + Python Instructions | 30% |
| 🤖 Agentic | Anthropic HH-RLHF | 10% |
| 🧮 Reasoning + Self | GSM8K + Self-Generated | 10% |
| Parameters | 3,808,939 |
| Layers | 6 |
| Embed dim | 256 |
| Heads | 8 |
| Block size | 128 |
| Vocab size | 1195 |
| Final loss | 0.8225 |
1import torch
2from huggingface_hub import hf_hub_download
3import json
4
5ckpt_path = hf_hub_download("usernamebetter/idk-prev-2", "minigpt_checkpoint.pth")
6vocab_path = hf_hub_download("usernamebetter/idk-prev-2", "vocab.json")
7
8with open(vocab_path) as f:
9 vocab = json.load(f)
10stoi = vocab["stoi"]
11itos = {int(k): v for k, v in vocab["itos"].items()}
12
13ckpt = torch.load(ckpt_path, map_location="cpu")
14model.load_state_dict(ckpt["model"])
15model.eval()