Spaces:

kaushik-harsh-99
/

tinystories-17m-webgpu

Running

App Files Files Community

tinystories-17m-webgpu

63.4 MB

Ctrl+K

Ctrl+K

2 contributors

History: 35 commits

kaushik-harsh-99's picture

kaushik-harsh-99

Fix flicker: delay progress overlay 400ms, fade-in on slow connections, never shown on fast

055391b 18 days ago

.gitattributes

1.56 kB
Switch web engine to Wllama (llama.cpp WebAssembly) running 4-bit Q4_0 GGUF model 18 days ago
README.md

724 Bytes
Upload folder using huggingface_hub 18 days ago
export_gguf.py

4.09 kB
Fix GGUF conversion with RoPE weight permutation: achieves 100% identical quality to PyTorch FP32 18 days ago
index.html

5.32 kB
Minimalist UI: lazy-load on Generate click, download progress bar, FP16 only, single temperature control 18 days ago
index.js

11.5 kB
Fix flicker: delay progress overlay 400ms, fade-in on slow connections, never shown on fast 18 days ago
model_f16.gguf

40.8 MB
xet

Add ?model=f16 param + push F16 GGUF for wllama F16 vs Q8 diagnostic test 18 days ago
model_q8_0.gguf

21.8 MB
xet

Fix GGUF conversion with RoPE weight permutation: achieves 100% identical quality to PyTorch FP32 18 days ago
special_tokens_map.json

552 Bytes
Upload folder using huggingface_hub 18 days ago
style.css

9.19 kB
Fix flicker: delay progress overlay 400ms, fade-in on slow connections, never shown on fast 18 days ago
tokenizer.json

769 kB
Upload folder using huggingface_hub 18 days ago
tokenizer_config.json

1.13 kB
Upload folder using huggingface_hub 18 days ago