commit 649709002c1603c3effdd41309b5b79f622d563b Author: ModelHub XC Date: Fri Jul 17 08:48:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: 0x3/functiongemma-finetuned-g1-multilingual Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..979a034 --- /dev/null +++ b/README.md @@ -0,0 +1,120 @@ +--- +language: + - en + - zh + - ja + - fr + - de + - es +license: apache-2.0 +base_model: google/functiongemma-270m-it +tags: + - robotics + - function-calling + - gemma + - lora + - fine-tuned + - edge-ai + - jetson + - multilingual +pipeline_tag: text-generation +library_name: transformers +--- + +# FunctionGemma Robot Actions (Multilingual) + +A fine-tuned [FunctionGemma 270M](https://huggingface.co/google/functiongemma-270m-it) model that converts natural language into structured robot action and emotion function calls. Supports **6 languages** with **98% accuracy** at **~59ms** on NVIDIA Jetson AGX Thor. + +## Supported Languages + +🇬🇧 English · 🇨🇳 中文 · 🇯🇵 日本語 · 🇫🇷 Français · 🇩🇪 Deutsch · 🇪🇸 Español + +## Example + +``` +Input: "Can you shake hands with me?" → robot_action(shake_hand) + show_emotion(happy) +Input: "跟我握手" → robot_action(shake_hand) + show_emotion(happy) +Input: "握手してください" → robot_action(shake_hand) + show_emotion(happy) +Input: "Serrez-moi la main" → robot_action(shake_hand) + show_emotion(happy) +Input: "Gib mir die Hand" → robot_action(shake_hand) + show_emotion(happy) +Input: "Dame la mano" → robot_action(shake_hand) + show_emotion(happy) + +Input: "我今天心情不好" → robot_action(stand_still) + show_emotion(sad) +Input: "あれは何ですか？" → robot_action(stand_still) + show_emotion(confused) +Input: "Raconte-moi une blague" → robot_action(stand_still) + show_emotion(think) +``` + +## Supported Actions + +| Action | Description | +|--------|-------------| +| `shake_hand` | Handshake gesture | +| `face_wave` | Wave hello / goodbye | +| `hands_up` | Raise both hands | +| `stand_still` | Stay idle (default for general conversation) | +| `show_hand` | Show open hand / present card for payment | +| `do_payment` | Do the payment / do the payment | +| `down_payment` | Finished the payment | + +## Supported Emotions + +| Emotion | Animation | +|---------|-----------| +| `happy` | Happy.riv | +| `sad` | Sad.riv | +| `excited` | Excited.riv | +| `confused` | Confused.riv | +| `curious` | Curious.riv | +| `think` | Think.riv | + + +Constrained decoding uses 2 forward passes instead of 33 autoregressive steps, achieving ~18x speedup over standard `model.generate()`. + +## Training Details + +| Parameter | Value | +|-----------|-------| +| Base model | `google/functiongemma-270m-it` | +| Method | LoRA (rank 8, alpha 16) | +| Training data | ~6,000 examples (545 English + ~5,450 multilingual) | +| Languages | English, Chinese, Japanese, French, German, Spanish | +| Epochs | 3 | +| Learning rate | 2e-4 | +| Batch size | 4 (effective 16 with gradient accumulation) | +| Max sequence length | 512 | +| Precision | bf16 | +| Hardware | NVIDIA RTX 5070 Ti (16 GB) | + +Multilingual training data was generated using Claude API — 2 natural phrasings per language per English prompt, resulting in diverse and natural expressions rather than literal translations. + +## Usage + +### Quick Start + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model = AutoModelForCausalLM.from_pretrained( + "OpenmindAGI/functiongemma-finetuned-g1-multilingual", + torch_dtype=torch.bfloat16, + device_map="auto", +) +tokenizer = AutoTokenizer.from_pretrained("OpenmindAGI/functiongemma-finetuned-g1-multilingual") +model.eval() +``` + +## Citation + +```bibtex +@misc{openmindagi-functiongemma-multilingual, + title={FunctionGemma Robot Actions (Multilingual)}, + author={OpenmindAGI}, + year={2025}, + url={https://huggingface.co/OpenmindAGI/functiongemma-finetuned-g1-multilingual} +} +``` + +## License + +Fine-tuned from [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it) under [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0). diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1629479 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,279 @@ +{%- macro format_parameters(properties, required) -%} + {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%} + {%- set ns = namespace(found_first=false) -%} + {%- for key, value in properties | dictsort -%} + {%- if key not in standard_keys -%} + {%- if ns.found_first %},{% endif -%} + {%- set ns.found_first = true -%} + {{- key }}:{description:{{ value['description'] }} + {%- if value['type'] | upper == 'STRING' -%} + {%- if value['enum'] -%} + ,enum:{{ format_argument(value['enum']) }} + {%- endif -%} + {%- elif value['type'] | upper == 'OBJECT' -%} + ,properties:{ + {%- if value['properties'] is defined and value['properties'] is mapping -%} + {{- format_parameters(value['properties'], value['required'] | default([])) -}} + {%- elif value is mapping -%} + {{- format_parameters(value, value['required'] | default([])) -}} + {%- endif -%} + } + {%- if value['required'] -%} + ,required:[ + {%- for item in value['required'] | default([]) -%} + {{- item -}} + {%- if not loop.last %},{% endif -%} + {%- endfor -%} + ] + {%- endif -%} + {%- elif value['type'] | upper == 'ARRAY' -%} + {%- if value['items'] is mapping and value['items'] -%} + ,items:{ + {%- set ns_items = namespace(found_first=false) -%} + {%- for item_key, item_value in value['items'] | dictsort -%} + {%- if item_value is not none -%} + {%- if ns_items.found_first %},{% endif -%} + {%- set ns_items.found_first = true -%} + {%- if item_key == 'properties' -%} + properties:{ + {%- if item_value is mapping -%} + {{- format_parameters(item_value, value['items']['required'] | default([])) -}} + {%- endif -%} + } + {%- elif item_key == 'required' -%} + required:[ + {%- for req_item in item_value -%} + {{- req_item -}} + {%- if not loop.last %},{% endif -%} + {%- endfor -%} + ] + {%- elif item_key == 'type' -%} + {%- if item_value is string -%} + type:{{ format_argument(item_value | upper) }} + {%- else -%} + type:{{ format_argument(item_value | map('upper') | list) }} + {%- endif -%} + {%- else -%} + {{ item_key }}:{{ format_argument(item_value) }} + {%- endif -%} + {%- endif -%} + {%- endfor -%} + } + {%- endif -%} + {%- endif -%} + ,type:{{ value['type'] | upper }}} + {%- endif -%} + {%- endfor -%} +{%- endmacro -%} +{% macro format_function_declaration(tool_data) -%} +declaration:{{- tool_data['function']['name'] -}} +{description:{{- tool_data['function']['description'] -}} +{%- set params = tool_data['function']['parameters'] -%} +{%- if params -%} + ,parameters:{ + {%- if params['properties'] -%} + properties:{ {{- format_parameters(params['properties'], params['required']) -}} }, + {%- endif -%} + {%- if params['required'] -%} + required:[ + {%- for item in params['required'] -%} + {{- item -}} + {{- ',' if not loop.last -}} + {%- endfor -%} + ], + {%- endif -%} + {%- if params['type'] -%} + type:{{- params['type'] | upper -}}} + {%- endif -%} +{%- endif -%} +} +{%- endmacro -%} +{% macro format_argument(argument, escape_keys=True) -%} +{%- if argument is string -%} + {{- '' + argument + '' -}} +{%- elif argument is boolean -%} + {%- if argument -%} + {{- 'true' -}} + {%- else -%} + {{- 'false' -}} + {%- endif -%} +{%- elif argument is mapping -%} + {{- '{' -}} + {%- set ns = namespace(found_first=false) -%} + {%- for key, value in argument | dictsort -%} + {%- if ns.found_first %},{% endif -%} + {%- set ns.found_first = true -%} + {%- if escape_keys -%} + {{- '' + key + '' -}} + {%- else -%} + {{- key -}} + {%- endif -%} + :{{- format_argument(value, escape_keys=escape_keys) -}} + {%- endfor -%} + {{- '}' -}} +{%- elif argument is sequence -%} + {{- '[' -}} + {%- for item in argument -%} + {{- format_argument(item, escape_keys=escape_keys) -}} + {%- if not loop.last %},{% endif -%} + {%- endfor -%} + {{- ']' -}} +{%- else -%} + {{- argument -}} +{%- endif -%} +{%- endmacro -%} +{{ bos_token }} +{%- set ns = namespace(prev_message_type=None) -%} +{#- Tool Declarations -#} +{%- set loop_messages = messages -%} +{%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%} + {{- 'developer\n' -}} + {%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%} + {%- if messages[0]['content'] is string -%} + {{- messages[0]['content'] | trim -}} + {%- elif messages[0]['content'] is sequence -%} + {%- for item in messages[0]['content'] -%} + {%- if item['type'] == 'text' -%} + {{- item['text'] | trim -}} + {%- endif -%} + {%- endfor -%} + {%- endif -%} + {%- set loop_messages = messages[1:] -%} + {%- endif -%} + {%- if tools -%} + {%- for tool in tools %} + {{- '' -}} + {{- format_function_declaration(tool) | trim }} + {{- '' -}} + {%- endfor %} + {%- endif -%} + {{- '\n' }} +{%- endif %} +{#- Loop through messages. -#} +{%- for message in loop_messages -%} + {%- if (message['role'] == 'assistant') -%} + {#- Rename "assistant" to "model". -#} + {%- set role = "model" -%} + {%- else -%} + {%- set role = message['role'] -%} + {%- endif -%} + {%- if role != 'tool' -%} + {%- if ns.prev_message_type != 'tool_response' -%} + {{- '' + role + '\n' }} + {%- endif -%} + {%- set ns.prev_message_type = None -%} + {%- if 'content' in message and message['content'] is not none -%} + {%- if message['content'] is string -%} + {{ message['content'] | trim }} + {%- elif message['content'] is sequence -%} + {%- for item in message['content'] -%} + {%- if item['type'] == 'image' -%} + {{ '' }} + {%- elif item['type'] == 'text' -%} + {{ item['text'] | trim }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{ raise_exception("Invalid content type in user/assistant message") }} + {%- endif -%} + {%- set ns.prev_message_type = 'content' -%} + {%- endif -%} + {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%} + {#- Tool Calls -#} + {%- for tool_call in message['tool_calls'] -%} + {% set function = tool_call['function'] %} + {{- 'call:' + function['name'] + '{' -}} + {%- if 'arguments' in function -%} + {%- if function['arguments'] is mapping -%} + {%- set ns = namespace(found_first=false) -%} + {%- for key, value in function['arguments'] | dictsort -%} + {%- if ns.found_first %},{% endif -%} + {%- set ns.found_first = true -%} + {{- key -}}:{{- format_argument(value, escape_keys=False) -}} + {%- endfor -%} + {%- elif function['arguments'] is string -%} + {# This handles string-JSON, just in case #} + {{ function['arguments'] }} + {%- endif %} + {%- endif -%} + {{- '}' -}} + {%- endfor -%} + {%- if loop.last -%} + {{ '' }} + {%- endif -%} + {%- set ns.prev_message_type = 'tool_call' -%} + {%- endif -%} + {%- else -%} + {#- Tool Responses -#} + {%- if 'content' in message and message['content'] -%} + {%- if message['content'] is mapping -%} + {%- if 'name' in message['content'] and 'response' in message['content'] -%} + {{ 'response:' + message['content']['name'] | trim + '{' }} + {%- set response_ns = namespace(found_first=false) -%} + {%- for key, value in message['content']['response'] | dictsort -%} + {%- if response_ns.found_first %},{% endif -%} + {%- set response_ns.found_first = true -%} + {{- key -}}:{{- format_argument(value, escape_keys=False) -}} + {%- endfor -%} + {{- '}' -}} + {%- elif 'name' in message -%} + {{ 'response:' + message['name'] | trim + '{' }} + {%- set response_ns = namespace(found_first=false) -%} + {%- for key, value in message['content'] | dictsort -%} + {%- if response_ns.found_first %},{% endif -%} + {%- set response_ns.found_first = true -%} + {{- key -}}:{{- format_argument(value, escape_keys=False) -}} + {%- endfor -%} + {{- '}' -}} + {%- else -%} + {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }} + {%- endif -%} + {%- elif message['content'] is string -%} + {%- if 'name' in message -%} + {{ 'response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}' }} + {%- else -%} + {{ raise_exception("Invalid tool response: 'name' must be provided.") }} + {%- endif -%} + {%- elif message['content'] is sequence -%} + {%- for item in message['content'] -%} + {%- if item is mapping -%} + {%- if 'name' in item and 'response' in item -%} + {{ 'response:' + item['name'] | trim + '{' }} + {%- set response_ns = namespace(found_first=false) -%} + {%- for key, value in item['response'] | dictsort -%} + {%- if response_ns.found_first %},{% endif -%} + {%- set response_ns.found_first = true -%} + {{- key -}}:{{- format_argument(value, escape_keys=False) -}} + {%- endfor -%} + {{- '}' -}} + {%- elif 'name' in message -%} + {{ 'response:' + message['name'] | trim + '{' }} + {%- set response_ns = namespace(found_first=false) -%} + {%- for key, value in item | dictsort -%} + {%- if response_ns.found_first %},{% endif -%} + {%- set response_ns.found_first = true -%} + {{- key -}}:{{- format_argument(value, escape_keys=False) -}} + {%- endfor -%} + {{- '}' -}} + {%- else -%} + {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }} + {%- endif -%} + {%- else -%} + {{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }} + {%- endif -%} + {%- endif -%} + {%- set ns.prev_message_type = 'tool_response' -%} + {%- endif -%} + {%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%} + {{ '\n' }} + {%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + {%- if ns.prev_message_type != 'tool_response' -%} + {{- 'model\n' -}} + {%- endif -%} +{%- endif -%} diff --git a/config.json b/config.json new file mode 100644 index 0000000..050fb25 --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "_sliding_window_pattern": 6, + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "dtype": "bfloat16", + "eos_token_id": 1, + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "full_attention": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_attention": { + "rope_theta": 10000.0, + "rope_type": "default" + } + }, + "sliding_window": 512, + "tie_word_embeddings": true, + "transformers_version": "5.3.0", + "use_bidirectional_attention": false, + "use_cache": false, + "vocab_size": 262146 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..d5cb0c3 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,15 @@ +{ + "bos_token_id": 2, + "cache_implementation": "hybrid", + "do_sample": true, + "eos_token_id": [ + 1, + 1, + 50, + 106 + ], + "pad_token_id": 0, + "top_k": 64, + "top_p": 0.95, + "transformers_version": "5.3.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..7cb6567 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9a3548f574cf3af2ef337d3e7d280ad76daecf493603a81030e0c4a4f751d1 +size 536225616 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..93a0904 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80d7f800b949accd7eb940bac75e642f9468e4df157403032a55bf54ed23b650 +size 33384898 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..255e9fe --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,26 @@ +{ + "backend": "tokenizers", + "boi_token": "", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eoi_token": "", + "eos_token": "", + "image_token": "", + "is_local": false, + "mask_token": "", + "model_max_length": 512, + "model_specific_special_tokens": { + "boi_token": "", + "eoi_token": "", + "image_token": "", + "sfr_token": "" + }, + "pad_token": "", + "padding_side": "left", + "sfr_token": "", + "sp_model_kwargs": null, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}