Mortdecai
eecebe7ef5
Five-lane parallel research pass. Each subdir under tooling/ has its own README indexing downloaded files with verified upstream sources. - google-official/: deepmind-gemma JAX examples, gemma_pytorch scripts, gemma.cpp API server docs, google-gemma/cookbook notebooks, ai.google.dev HTML snapshots, Gemma 3 tech report - huggingface/: 8 gemma-4-* model cards, chat-template .jinja files, tokenizer_config.json, transformers gemma4/ source, launch blog posts, official HF Spaces app.py - inference-frameworks/: vLLM/llama.cpp/MLX/Keras-hub/TGI/Gemini API/Vertex AI comparison, run_commands.sh with 8 working launches, 9 code snippets - gemma-family/: 12 per-variant briefs (ShieldGemma 2, CodeGemma, PaliGemma 2, Recurrent/Data/Med/TxGemma, Embedding/Translate/Function/Dolphin/SignGemma) - fine-tuning/: Unsloth Gemma 4 notebooks, Axolotl YAMLs (incl 26B-A4B MoE), TRL scripts, Google cookbook fine-tune notebooks, recipe-recommendation.md Findings that update earlier CORPUS_* docs are flagged in tooling/README.md (not applied) — notably the new <|turn>/<turn|> prompt format, gemma_pytorch abandonment, gemma.cpp Gemini-API server, transformers AutoModelForMultimodalLM, FA2 head_dim=512 break, 26B-A4B MoE quantization rules, no Gemma 4 tech report PDF yet, no Gemma-4-generation specialized siblings yet. Pre-commit secrets hook bypassed per user authorization — flagged "secrets" are base64 notebook cell outputs and example Ed25519 keys in the HDP agentic-security demo, not real credentials. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
75 lines
2.0 KiB
JSON
75 lines
2.0 KiB
JSON
{
|
|
"audio_token": "<|audio|>",
|
|
"backend": "tokenizers",
|
|
"boa_token": "<|audio>",
|
|
"boi_token": "<|image>",
|
|
"bos_token": "<bos>",
|
|
"eoa_token": "<audio|>",
|
|
"eoc_token": "<channel|>",
|
|
"eoi_token": "<image|>",
|
|
"eos_token": "<eos>",
|
|
"eot_token": "<turn|>",
|
|
"escape_token": "<|\"|>",
|
|
"etc_token": "<tool_call|>",
|
|
"etd_token": "<tool|>",
|
|
"etr_token": "<tool_response|>",
|
|
"extra_special_tokens": [
|
|
"<|video|>"
|
|
],
|
|
"image_token": "<|image|>",
|
|
"mask_token": "<mask>",
|
|
"model_max_length": 1000000000000000019884624838656,
|
|
"pad_token": "<pad>",
|
|
"padding_side": "left",
|
|
"processor_class": "Gemma4Processor",
|
|
"response_schema": {
|
|
"type": "object",
|
|
"properties": {
|
|
"role": {
|
|
"const": "assistant"
|
|
},
|
|
"thinking": {
|
|
"type": "string"
|
|
},
|
|
"content": {
|
|
"type": "string"
|
|
},
|
|
"tool_calls": {
|
|
"x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"const": "function"
|
|
},
|
|
"function": {
|
|
"type": "object",
|
|
"x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
|
|
"properties": {
|
|
"name": {
|
|
"type": "string"
|
|
},
|
|
"arguments": {
|
|
"type": "object",
|
|
"x-parser": "gemma4-tool-call",
|
|
"additionalProperties": {}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
|
|
},
|
|
"soc_token": "<|channel>",
|
|
"sot_token": "<|turn>",
|
|
"stc_token": "<|tool_call>",
|
|
"std_token": "<|tool>",
|
|
"str_token": "<|tool_response>",
|
|
"think_token": "<|think|>",
|
|
"tokenizer_class": "GemmaTokenizer",
|
|
"unk_token": "<unk>"
|
|
}
|