Commit History
9 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 signaturee6df45c
-
Card: measured device / browser results (edge-compat, 2026-09)
Verified signature6960f53 -
Card: compatibility line (edge-compat, 2026-09)
Verified signature290d603
-
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 signature0969aad
-
Add litertlm_manifest.json (deployment manifest 0.1.2: variant selection, verified backends, Android/Apple recommendations, measured rows with conditions)
Verified signature02d2d23 -
Card: base_model_relation: quantized (list under the base model's Quantizations)
Verified signature395b47e
-
Card: note the chat-template fix for role-'assistant' history (weights unchanged)
Verified signatured3e50be -
Chat template fix (metadata-only, weights unchanged): the template matched history turns only on role 'model', so a conversation created through the Conversation API with the standard role 'assistant' (e.g. create_conversation(messages=[...]) restoring a chat) silently dropped every assistant turn from the rendered prompt. The role conditions now also accept 'assistant'. Every other section is byte-identical; single-turn renders, token ids, prefill and greedy answers are unchanged (verified on the LiteRT-LM runtime). See google-ai-edge/LiteRT-LM#3417.
Verified signature0c77b1e
-
Card: note the tokenizer-section fix (weights unchanged)
Verified signaturec634310 -
Replace the tokenizer section with the upstream tokenizer.json (weights, graph and metadata unchanged). The previous SentencePiece conversion of the BPE tokenizer encoded standalone accented/special characters to the wrong ids, turned characters without a vocabulary entry (emoji, some accented capitals) into the end-of-text/end-of-turn token, and could not match the token it had reused as UNK; prompts now tokenize identically to the upstream tokenizer (verified on the LiteRT-LM runtime, see the card note).
Verified signature030c838
-
Card: note the default-system-prompt fix (weights unchanged)
Verified signature3d8492f -
Restore the vendor's default system prompt in the chat template (weights unchanged). The converter's template probe never renders the block the upstream template emits when the caller sends no system message, so the bundle silently dropped it; with no system message the prompt now renders byte-identical to the upstream chat template's output (see the card note).
Verified signature77c0c27 -
Card: correct the start_token note — measured numbers do not carry over
Verified signature790cbe6 -
Card: note the start_token fix (weights unchanged)
Verified signatureb73648d -
Drop the metadata start_token (weights unchanged)
Verified signatureThe metadata start_token held the literal string "None" (this tokenizer has no BOS), and the engine resolved it to a real vocabulary token - so every prompt began with the word "None", a stream the model was never trained on. Metadata-only change: every tokenizer and TFLite section is byte-identical to the previous file (verified by sha256 per section), so quality and speed are unchanged and the card's measured numbers still stand.402a871
-
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.cd1ba8b
-
Card: state where each on-device figure actually comes from; replace the iPhone row with a fresh measurement where one was taken
Verified signature2c0bf05 -
Card: verified one-command usage, measured Performance table (backends gated on real generation), accuracy note
Verified signatureb73757b
-
Document Gallery 1.0.16 direct Hugging Face import + desktop LiteRT-LM CLI (serve/run)
Verified signature693605b
-
Upload README.md with huggingface_hub
Verified signature90055a9 -
Upload README.md with huggingface_hub
Verified signature09a73e1 -
Upload InternVL3-2B.litertlm with huggingface_hub
Verified signaturecfb3023 -
Upload README.md with huggingface_hub
Verified signaturec97552b -
Upload README.md with huggingface_hub
Verified signature8578bfb -
Upload InternVL3-2B.litertlm with huggingface_hub
Verified signature6af4ebf -
Upload InternVL3-2B.litertlm with huggingface_hub
Verified signature8e501bd -
Upload README.md with huggingface_hub
Verified signature6eb5a32 -
initial commit
Verified signatureff4c99b