feat(phase-04): Wyoming Satellite integration + OpenClaw HA components
## Voice Pipeline (P3) - Replace openWakeWord daemon with Wyoming Satellite approach - Add Wyoming Satellite service on port 10700 for HA voice pipeline - Update setup.sh with cross-platform sed compatibility (macOS/Linux) - Add version field to Kokoro TTS voice info - Update launchd service loader to use Wyoming Satellite ## Home Assistant Integration (P4) - Add custom conversation agent component (openclaw_conversation) - Fix: Use IntentResponse instead of plain strings (HA API requirement) - Support both HTTP API and CLI fallback modes - Config flow for easy HA UI setup - Add OpenClaw bridge scripts (Python + Bash) - Add ha-ctl utility for HA entity control - Fix: Use context manager for token file reading - Add HA configuration examples and documentation ## Infrastructure - Add mem0 backup automation (launchd + script) - Add n8n workflow templates (morning briefing, notification router) - Add VS Code workspace configuration - Reorganize model files into categorized folders: - lmstudio-community/ - mlx-community/ - bartowski/ - mradermacher/ ## Documentation - Update PROJECT_PLAN.md with Wyoming Satellite architecture - Update TODO.md with completed Wyoming integration tasks - Add OPENCLAW_INTEGRATION.md for HA setup guide ## Testing - Verified Wyoming services running (STT:10300, TTS:10301, Satellite:10700) - Verified OpenClaw CLI accessibility - Confirmed cross-platform compatibility fixes
This commit is contained in:
Aodhan Collins
@@ -0,0 +1,117 @@
|
||||
{% macro render_extra_keys(json_dict, handled_keys) %}
|
||||
{%- if json_dict is mapping %}
|
||||
{%- for json_key in json_dict if json_key not in handled_keys %}
|
||||
{%- if json_dict[json_key] is string %}
|
||||
{{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
|
||||
{%- else %}
|
||||
{{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson) ~ '</' ~ json_key ~ '>' }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{%- endmacro %}
|
||||
|
||||
{%- if messages[0]["role"] == "system" %}
|
||||
{%- set system_message = messages[0]["content"] %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
|
||||
{%- if not tools is defined %}
|
||||
{%- set tools = [] %}
|
||||
{%- endif %}
|
||||
|
||||
{%- if system_message is defined %}
|
||||
{{- "<|im_start|>system\n" + system_message }}
|
||||
{%- else %}
|
||||
{%- if tools is iterable and tools | length > 0 %}
|
||||
{{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if tools is iterable and tools | length > 0 %}
|
||||
{{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
|
||||
{{- "<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{%- if tool.function is defined %}
|
||||
{%- set tool = tool.function %}
|
||||
{%- endif %}
|
||||
{{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
|
||||
{%- if tool.description is defined %}
|
||||
{{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
|
||||
{%- endif %}
|
||||
{{- '\n<parameters>' }}
|
||||
{%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
|
||||
{%- for param_name, param_fields in tool.parameters.properties|items %}
|
||||
{{- '\n<parameter>' }}
|
||||
{{- '\n<name>' ~ param_name ~ '</name>' }}
|
||||
{%- if param_fields.type is defined %}
|
||||
{{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
|
||||
{%- endif %}
|
||||
{%- if param_fields.description is defined %}
|
||||
{{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
|
||||
{%- endif %}
|
||||
{%- set handled_keys = ['name', 'type', 'description'] %}
|
||||
{{- render_extra_keys(param_fields, handled_keys) }}
|
||||
{{- '\n</parameter>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{%- set handled_keys = ['type', 'properties'] %}
|
||||
{{- render_extra_keys(tool.parameters, handled_keys) }}
|
||||
{{- '\n</parameters>' }}
|
||||
{%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
|
||||
{{- render_extra_keys(tool, handled_keys) }}
|
||||
{{- '\n</function>' }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>" }}
|
||||
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
||||
{%- endif %}
|
||||
{%- if system_message is defined %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{%- if tools is iterable and tools | length > 0 %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
|
||||
{{- '\n' + message.content | trim + '\n' }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
||||
{%- if tool_call.arguments is defined %}
|
||||
{%- for args_name, args_value in tool_call.arguments|items %}
|
||||
{{- '<parameter=' + args_name + '>\n' }}
|
||||
{%- set args_value = args_value if args_value is string else args_value | tojson %}
|
||||
{{- args_value }}
|
||||
{{- '\n</parameter>\n' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '</function>\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif loop.last %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
@@ -0,0 +1,825 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3NextForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0,
|
||||
"bos_token_id": 151643,
|
||||
"decoder_sparse_step": 1,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"full_attention_interval": 4,
|
||||
"head_dim": 256,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 5120,
|
||||
"linear_conv_kernel_dim": 4,
|
||||
"linear_key_head_dim": 128,
|
||||
"linear_num_key_heads": 16,
|
||||
"linear_num_value_heads": 32,
|
||||
"linear_value_head_dim": 128,
|
||||
"max_position_embeddings": 262144,
|
||||
"mlp_only_layers": [],
|
||||
"model_type": "qwen3_next",
|
||||
"moe_intermediate_size": 512,
|
||||
"norm_topk_prob": true,
|
||||
"num_attention_heads": 16,
|
||||
"num_experts": 512,
|
||||
"num_experts_per_tok": 10,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 2,
|
||||
"output_router_logits": false,
|
||||
"partial_rotary_factor": 0.25,
|
||||
"quantization": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine",
|
||||
"model.layers.0.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.0.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.1.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.1.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.2.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.2.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.3.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.3.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.4.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.4.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.5.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.5.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.6.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.6.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.7.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.7.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.8.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.8.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.9.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.9.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.10.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.10.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.11.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.11.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.12.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.12.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.13.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.13.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.14.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.14.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.15.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.15.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.16.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.16.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.17.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.17.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.18.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.18.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.19.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.19.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.20.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.20.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.21.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.21.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.22.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.22.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.23.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.23.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.24.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.24.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.25.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.25.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.26.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.26.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.27.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.27.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.28.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.28.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.29.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.29.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.30.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.30.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.31.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.31.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.32.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.32.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.33.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.33.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.34.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.34.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.35.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.35.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.36.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.36.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.37.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.37.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.38.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.38.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.39.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.39.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.40.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.40.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.41.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.41.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.42.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.42.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.43.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.43.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.44.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.44.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.45.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.45.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.46.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.46.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.47.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.47.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
}
|
||||
},
|
||||
"quantization_config": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine",
|
||||
"model.layers.0.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.0.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.1.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.1.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.2.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.2.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.3.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.3.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.4.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.4.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.5.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.5.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.6.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.6.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.7.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.7.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.8.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.8.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.9.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.9.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.10.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.10.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.11.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.11.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.12.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.12.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.13.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.13.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.14.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.14.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.15.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.15.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.16.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.16.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.17.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.17.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.18.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.18.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.19.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.19.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.20.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.20.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.21.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.21.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.22.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.22.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.23.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.23.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.24.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.24.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.25.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.25.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.26.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.26.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.27.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.27.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.28.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.28.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.29.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.29.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.30.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.30.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.31.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.31.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.32.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.32.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.33.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.33.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.34.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.34.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.35.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.35.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.36.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.36.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.37.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.37.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.38.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.38.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.39.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.39.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.40.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.40.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.41.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.41.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.42.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.42.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.43.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.43.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.44.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.44.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.45.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.45.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.46.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.46.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.47.mlp.gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
},
|
||||
"model.layers.47.mlp.shared_expert_gate": {
|
||||
"group_size": 64,
|
||||
"bits": 8
|
||||
}
|
||||
},
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 5000000,
|
||||
"router_aux_loss_coef": 0.001,
|
||||
"shared_expert_intermediate_size": 512,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.57.0.dev0",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 1.0,
|
||||
"top_k": 40,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.3"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user