Commit History
8 days ago
-
manifest 0.1.3: capabilities.thinking.control = never (what the bundle's template does about thinking, derived from the template inside the bundle)
Verified signature30b4519
-
Card: definition line (LiteRT, 2026-09)
Verified signaturef9b3581
-
manifest: same-device CPU control rows on the Galaxy S26 for the flagship GPU recommendation (S7 backfill 2026-09-05); the recommendation is rewritten from the measured pair (measured win, kept for prefill, or reversed to cpu)
Verified signature057e1d1
-
Add litertlm_manifest.json (deployment manifest 0.1.2: variant selection, verified backends, Android/Apple recommendations, measured rows with conditions)
Verified signature702b88e -
Card: base_model_relation: quantized (list under the base model's Quantizations)
Verified signature182bbb3
-
Add measured Raspberry Pi 5 (CPU) section
Verified signatureNumbers from the 2026-09 Raspberry Pi 5 LLM sweep: litert-lm benchmark 0.16.1, CPU backend, 4 threads, 256 prefill + 256 decode tokens, compile cache disabled, 3 invocations per file with cooldown, thermal throttle state verified 0x0 on every run, and a real-generation gate on the same backend before any number was recorded. Median + spread, never single-shot.555422e
-
Card: note the tokenizer-section fix (weights unchanged)
Verified signature8f833d1 -
Replace the embedded tokenizer.json with the upstream one (weights, graph and metadata unchanged). The previous copy carried the GPT-2 default pre-tokenizer instead of the model's own regex, so digits and punctuation before newlines split differently from the upstream tokenizer on every turn; prompts now tokenize identically (see the card note).
Verified signaturef94e362
-
Add measured Galaxy S26 GPU backend section
Verified signatureFunctional verdict from the S26 GPU gate. Primary log: litertlm-convert/community_accel_work/s4_gpu_gate/results.jsonl. Delegation counts and peak RSS are read from that run's own log; throughput is deliberately absent, because an Android GPU speed is not quotable without a CPU row from the same phone and that control has not been run.f2c6c40
-
Card: measured Performance table (M4 Max CPU/GPU + on-device where measured), accuracy note
Verified signature008b3f3
-
Card: add measured Performance table (M4 Max CPU/GPU + iPhone 17 Pro), accuracy note, verified one-command usage
Verified signature6110d17
-
Document Gallery 1.0.16 direct Hugging Face import + desktop LiteRT-LM CLI (serve/run)
Verified signature56fd1f4
-
docs: add Training data & PII section (submission-guideline compliance)
Verified signaturec2d0471
-
Upload folder using huggingface_hub
Verified signaturea742c8e -
initial commit
Verified signature2dda6d4