Commit History
16 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 signaturecd26ba8
-
Add litertlm_manifest.json (deployment manifest 0.1.2: variant selection, verified backends, Android/Apple recommendations, measured rows with conditions)
Verified signature392b2a7 -
Card: base_model_relation: quantized (list under the base model's Quantizations)
Verified signature844bad0
-
Card: note the chat-template fix for role-'assistant' history (weights unchanged)
Verified signaturecfc4574 -
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 signature36e7fe0
-
Card: note the tokenizer-section fix (weights unchanged)
Verified signature32a4f75 -
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 signaturec48c64f
-
Card: note the default-system-prompt fix (weights unchanged)
Verified signature0a9ac5b -
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 signature3b71135 -
Card: correct the start_token note — measured numbers do not carry over
Verified signature3fd52bb -
Card: note the start_token fix (weights unchanged)
Verified signaturea64880f -
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.5a5cdca
-
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.17fac85
-
Card: state where each on-device figure actually comes from; replace the iPhone row with a fresh measurement where one was taken
Verified signature644c14d -
Card: verified one-command usage, measured Performance table (backends gated on real generation), accuracy note
Verified signature7a36646
-
Upload Mage-VL.litertlm with huggingface_hub
Verified signaturec53b773 -
Upload README.md with huggingface_hub
Verified signaturebf9a53e -
initial commit
Verified signaturedfb0a3a