Views
No views yet
1.8157 (at step 202,000)| File Name | Quantization | Size | Description |
|---|---|---|---|
Simple-Stories-Hindi-11M-F16.gguf | F16 (16-bit Float) | ~22.0 MB | Full 16-bit float precision GGUF format |
| Parameter | Value |
|---|---|
| Parameters | 11.45M total (10.17M non-embedding) |
| Architecture | LLaMA-style (RoPE + SwiGLU + RMSNorm) |
| Context Length | 512 tokens |
Embedding Dim (d_model) | 320 |
| FFN Hidden Dim | 896 |
| Layers | 7 |
| Attention Heads | 5 |
| Vocabulary | 4,000 (SentencePiece Unigram) |
llama.cpp CLI1./llama-cli -m Simple-Stories-Hindi-11M-F16.gguf \
2 -p "एक समय की बात है" \
3 -n 150 \
4 --temp 0.8 \
5 --top-k 40 \
6 --top-p 0.95llama-cpp-python1from llama_cpp import Llama
2
3llm = Llama(
4 model_path="Simple-Stories-Hindi-11M-F16.gguf",
5 n_ctx=512,
6 verbose=False
7)
8
9output = llm(
10 "एक समय की बात है",
11 max_tokens=150,
12 temperature=0.8,
13 top_k=40,
14 top_p=0.95
15)
16
17print(output["choices"][0]["text"])