Commit History

Multi-turn UX: new-chat button; example click resets conversation; 1k-token sliding-window history; 4th example (sleep)
a284b48
Running
verified

codelion commited on

INT8 dynamic quant (~2x CPU, verified all 3 modes); add self-spec to chat mode selector
873a061
verified

codelion commited on

Compare/chat prompts: drop count-based "three tips" (looks truncated at 48 tok); use self-contained short-answer prompts (ocean / neural net / exercise)
0249a53
verified

codelion commited on

Fix chat crash: gradio 6 Chatbot content is a list of parts; flatten to text before apply_chat_template
1ed429f
verified

codelion commited on

Fix gradio 6.14: gr.Chatbot dropped the type= arg (messages is default)
f411959
verified

codelion commited on

Custom chat layout: compact mode/max-tokens/temp controls above input; single-column examples (readable); header link to codelion/dhara-250m
df2112c
verified

codelion commited on

Disable example caching (HF Spaces defaults cache_examples=True) so example clicks generate live, not pre-baked
4681623
verified

codelion commited on

Coherence: rep-penalty 1.3 in diffusion/self-spec (no more collapse); clip to last full sentence (no mid-word cutoff); exposed config panel (mode/max-tokens/temperature); greedy AR in compare; better default prompts
7c0285b
verified

codelion commited on

Fix gradio 6 build: examples as list-of-lists (additional_inputs); move theme/css to launch()
cf976b5
verified

codelion commited on

Chat mode toggle (AR/diffusion w/ live β–“β–’β–‘ denoise); streaming 3-mode compare reveal; max_new 128 + no_repeat_ngram
732ea5f
verified

codelion commited on

Fixed-height scrollable chat; pass attention_mask (silence pad==eos warning); _enc helper
a36cfa9
verified

codelion commited on

Denoiser-terminal UI (mask-glyph aesthetic, amber CRT) + streaming per-mode compare with progress
32de77f
verified

codelion commited on

Link model (models: codelion/dhara-250m) for Spaces-using-this-model widget
3ecfd57
verified

codelion commited on

Add torch to requirements (gradio SDK base has no torch)
7638ff6
verified

codelion commited on

remove Dockerfile (switched to gradio SDK)
619b3a2
verified

codelion commited on

gradio SDK 6.14.0 (proven to import with hub 1.16) + transformers 5.5 + messages-format app
51b846a
verified

codelion commited on

Pin gradio==4.44.1 + use 4.x tuples ChatInterface API (model already loads)
1a232f4
verified

codelion commited on

Switch to Docker SDK; pip-resolved transformers==5.5.0 + gradio (fixes tokenizer/HfFolder)
a54a16a
verified

codelion commited on

Pin coherent stack (py3.12, gradio4.44, transformers<5, hub<1) to fix HfFolder/audioop; title ChatDhara
a113c18
verified

codelion commited on

Fix py3.13 gradio import: add audioop-lts (audioop removed in 3.13)
e2c8b3f
verified

codelion commited on

dhara-chat tri-mode CPU demo
78e793b
verified

codelion commited on

initial commit
bca5486
verified

codelion commited on