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 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
@@ -0,0 +1,120 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{%- if messages[0].content is string %}
|
||||
{{- messages[0].content }}
|
||||
{%- else %}
|
||||
{%- for content in messages[0].content %}
|
||||
{%- if 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].content is string %}
|
||||
{{- messages[0].content }}
|
||||
{%- else %}
|
||||
{%- for content in messages[0].content %}
|
||||
{%- if 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set image_count = namespace(value=0) %}
|
||||
{%- set video_count = namespace(value=0) %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.role == "user" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' }}
|
||||
{%- if message.content is string %}
|
||||
{{- message.content }}
|
||||
{%- else %}
|
||||
{%- for content in message.content %}
|
||||
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
||||
{%- set image_count.value = image_count.value + 1 %}
|
||||
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
||||
<|vision_start|><|image_pad|><|vision_end|>
|
||||
{%- elif content.type == 'video' or 'video' in content %}
|
||||
{%- set video_count.value = video_count.value + 1 %}
|
||||
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
||||
<|vision_start|><|video_pad|><|vision_end|>
|
||||
{%- elif 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' }}
|
||||
{%- if message.content is string %}
|
||||
{{- message.content }}
|
||||
{%- else %}
|
||||
{%- for content_item in message.content %}
|
||||
{%- if 'text' in content_item %}
|
||||
{{- content_item.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and message.content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{%- if message.content is string %}
|
||||
{{- message.content }}
|
||||
{%- else %}
|
||||
{%- for content in message.content %}
|
||||
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
||||
{%- set image_count.value = image_count.value + 1 %}
|
||||
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
||||
<|vision_start|><|image_pad|><|vision_end|>
|
||||
{%- elif content.type == 'video' or 'video' in content %}
|
||||
{%- set video_count.value = video_count.value + 1 %}
|
||||
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
||||
<|vision_start|><|video_pad|><|vision_end|>
|
||||
{%- elif 'text' in content %}
|
||||
{{- content.text }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
File diff suppressed because one or more lines are too long
@@ -0,0 +1,253 @@
|
||||
{
|
||||
"add_cross_attention": false,
|
||||
"architectures": [
|
||||
"Qwen3VLMoeForConditionalGeneration"
|
||||
],
|
||||
"bad_words_ids": null,
|
||||
"begin_suppress_tokens": null,
|
||||
"bos_token_id": null,
|
||||
"chunk_size_feed_forward": 0,
|
||||
"cross_attention_hidden_size": null,
|
||||
"decoder_start_token_id": null,
|
||||
"diversity_penalty": 0.0,
|
||||
"do_sample": false,
|
||||
"dtype": null,
|
||||
"early_stopping": false,
|
||||
"encoder_no_repeat_ngram_size": 0,
|
||||
"eos_token_id": null,
|
||||
"exponential_decay_length_penalty": null,
|
||||
"finetuning_task": null,
|
||||
"forced_bos_token_id": null,
|
||||
"forced_eos_token_id": null,
|
||||
"id2label": {
|
||||
"0": "LABEL_0",
|
||||
"1": "LABEL_1"
|
||||
},
|
||||
"image_token_id": 151655,
|
||||
"is_decoder": false,
|
||||
"is_encoder_decoder": false,
|
||||
"label2id": {
|
||||
"LABEL_0": 0,
|
||||
"LABEL_1": 1
|
||||
},
|
||||
"length_penalty": 1.0,
|
||||
"max_length": 20,
|
||||
"min_length": 0,
|
||||
"model_type": "qwen3_vl_moe",
|
||||
"no_repeat_ngram_size": 0,
|
||||
"num_beam_groups": 1,
|
||||
"num_beams": 1,
|
||||
"num_return_sequences": 1,
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"output_scores": false,
|
||||
"pad_token_id": null,
|
||||
"prefix": null,
|
||||
"problem_type": null,
|
||||
"pruned_heads": {},
|
||||
"quantization": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine"
|
||||
},
|
||||
"quantization_config": {
|
||||
"group_size": 64,
|
||||
"bits": 4,
|
||||
"mode": "affine"
|
||||
},
|
||||
"remove_invalid_values": false,
|
||||
"repetition_penalty": 1.0,
|
||||
"return_dict": true,
|
||||
"return_dict_in_generate": false,
|
||||
"sep_token_id": null,
|
||||
"suppress_tokens": null,
|
||||
"task_specific_params": null,
|
||||
"temperature": 1.0,
|
||||
"text_config": {
|
||||
"vocab_size": 151936,
|
||||
"max_position_embeddings": 262144,
|
||||
"hidden_size": 2048,
|
||||
"intermediate_size": 6144,
|
||||
"num_hidden_layers": 48,
|
||||
"num_attention_heads": 32,
|
||||
"num_key_value_heads": 4,
|
||||
"hidden_act": "silu",
|
||||
"initializer_range": 0.02,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"use_cache": true,
|
||||
"rope_theta": 5000000,
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"rope_scaling": {
|
||||
"mrope_interleaved": true,
|
||||
"mrope_section": [
|
||||
24,
|
||||
20,
|
||||
20
|
||||
],
|
||||
"rope_type": "default"
|
||||
},
|
||||
"head_dim": 128,
|
||||
"decoder_sparse_step": 1,
|
||||
"moe_intermediate_size": 768,
|
||||
"num_experts_per_tok": 8,
|
||||
"num_experts": 128,
|
||||
"norm_topk_prob": true,
|
||||
"router_aux_loss_coef": 0.001,
|
||||
"mlp_only_layers": [],
|
||||
"return_dict": true,
|
||||
"output_hidden_states": false,
|
||||
"torchscript": false,
|
||||
"dtype": "bfloat16",
|
||||
"pruned_heads": {},
|
||||
"tie_word_embeddings": false,
|
||||
"chunk_size_feed_forward": 0,
|
||||
"is_encoder_decoder": false,
|
||||
"is_decoder": false,
|
||||
"cross_attention_hidden_size": null,
|
||||
"add_cross_attention": false,
|
||||
"tie_encoder_decoder": false,
|
||||
"architectures": null,
|
||||
"finetuning_task": null,
|
||||
"id2label": {
|
||||
"0": "LABEL_0",
|
||||
"1": "LABEL_1"
|
||||
},
|
||||
"label2id": {
|
||||
"LABEL_0": 0,
|
||||
"LABEL_1": 1
|
||||
},
|
||||
"task_specific_params": null,
|
||||
"problem_type": null,
|
||||
"tokenizer_class": null,
|
||||
"prefix": null,
|
||||
"bos_token_id": 151643,
|
||||
"pad_token_id": null,
|
||||
"eos_token_id": 151645,
|
||||
"sep_token_id": null,
|
||||
"decoder_start_token_id": null,
|
||||
"max_length": 20,
|
||||
"min_length": 0,
|
||||
"do_sample": false,
|
||||
"early_stopping": false,
|
||||
"num_beams": 1,
|
||||
"temperature": 1.0,
|
||||
"top_k": 50,
|
||||
"top_p": 1.0,
|
||||
"typical_p": 1.0,
|
||||
"repetition_penalty": 1.0,
|
||||
"length_penalty": 1.0,
|
||||
"no_repeat_ngram_size": 0,
|
||||
"encoder_no_repeat_ngram_size": 0,
|
||||
"bad_words_ids": null,
|
||||
"num_return_sequences": 1,
|
||||
"output_scores": false,
|
||||
"return_dict_in_generate": false,
|
||||
"forced_bos_token_id": null,
|
||||
"forced_eos_token_id": null,
|
||||
"remove_invalid_values": false,
|
||||
"exponential_decay_length_penalty": null,
|
||||
"suppress_tokens": null,
|
||||
"begin_suppress_tokens": null,
|
||||
"num_beam_groups": 1,
|
||||
"diversity_penalty": 0.0,
|
||||
"_name_or_path": "",
|
||||
"model_type": "qwen3_vl_moe_text",
|
||||
"tf_legacy_loss": false,
|
||||
"use_bfloat16": false,
|
||||
"output_attentions": false
|
||||
},
|
||||
"tf_legacy_loss": false,
|
||||
"tie_encoder_decoder": false,
|
||||
"tie_word_embeddings": false,
|
||||
"tokenizer_class": null,
|
||||
"top_k": 50,
|
||||
"top_p": 1.0,
|
||||
"torchscript": false,
|
||||
"transformers_version": "4.57.0",
|
||||
"typical_p": 1.0,
|
||||
"use_bfloat16": false,
|
||||
"video_token_id": 151656,
|
||||
"vision_config": {
|
||||
"return_dict": true,
|
||||
"output_hidden_states": false,
|
||||
"torchscript": false,
|
||||
"dtype": null,
|
||||
"pruned_heads": {},
|
||||
"tie_word_embeddings": true,
|
||||
"chunk_size_feed_forward": 0,
|
||||
"is_encoder_decoder": false,
|
||||
"is_decoder": false,
|
||||
"cross_attention_hidden_size": null,
|
||||
"add_cross_attention": false,
|
||||
"tie_encoder_decoder": false,
|
||||
"architectures": null,
|
||||
"finetuning_task": null,
|
||||
"id2label": {
|
||||
"0": "LABEL_0",
|
||||
"1": "LABEL_1"
|
||||
},
|
||||
"label2id": {
|
||||
"LABEL_0": 0,
|
||||
"LABEL_1": 1
|
||||
},
|
||||
"task_specific_params": null,
|
||||
"problem_type": null,
|
||||
"tokenizer_class": null,
|
||||
"prefix": null,
|
||||
"bos_token_id": null,
|
||||
"pad_token_id": null,
|
||||
"eos_token_id": null,
|
||||
"sep_token_id": null,
|
||||
"decoder_start_token_id": null,
|
||||
"max_length": 20,
|
||||
"min_length": 0,
|
||||
"do_sample": false,
|
||||
"early_stopping": false,
|
||||
"num_beams": 1,
|
||||
"temperature": 1.0,
|
||||
"top_k": 50,
|
||||
"top_p": 1.0,
|
||||
"typical_p": 1.0,
|
||||
"repetition_penalty": 1.0,
|
||||
"length_penalty": 1.0,
|
||||
"no_repeat_ngram_size": 0,
|
||||
"encoder_no_repeat_ngram_size": 0,
|
||||
"bad_words_ids": null,
|
||||
"num_return_sequences": 1,
|
||||
"output_scores": false,
|
||||
"return_dict_in_generate": false,
|
||||
"forced_bos_token_id": null,
|
||||
"forced_eos_token_id": null,
|
||||
"remove_invalid_values": false,
|
||||
"exponential_decay_length_penalty": null,
|
||||
"suppress_tokens": null,
|
||||
"begin_suppress_tokens": null,
|
||||
"num_beam_groups": 1,
|
||||
"diversity_penalty": 0.0,
|
||||
"_name_or_path": "",
|
||||
"model_type": "qwen3_vl_moe",
|
||||
"tf_legacy_loss": false,
|
||||
"use_bfloat16": false,
|
||||
"depth": 27,
|
||||
"hidden_size": 1152,
|
||||
"hidden_act": "gelu_pytorch_tanh",
|
||||
"intermediate_size": 4304,
|
||||
"num_heads": 16,
|
||||
"in_channels": 3,
|
||||
"patch_size": 16,
|
||||
"spatial_merge_size": 2,
|
||||
"temporal_patch_size": 2,
|
||||
"out_hidden_size": 2048,
|
||||
"num_position_embeddings": 2304,
|
||||
"initializer_range": 0.02,
|
||||
"deepstack_visual_indexes": [
|
||||
8,
|
||||
16,
|
||||
24
|
||||
],
|
||||
"output_attentions": false
|
||||
},
|
||||
"vision_end_token_id": 151653,
|
||||
"vision_start_token_id": 151652
|
||||
}
|
||||
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"pad_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"top_p": 0.8,
|
||||
"top_k": 20,
|
||||
"temperature": 0.7,
|
||||
"repetition_penalty": 1.0,
|
||||
"transformers_version": "4.56.0"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,889 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 62141508064
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00013-of-00013.safetensors",
|
||||
"model.language_model.embed_tokens.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.0.mlp.experts.down_proj": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.0.mlp.gate.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.1.mlp.experts.down_proj": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.1.mlp.gate.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.10.mlp.experts.down_proj": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.10.mlp.gate.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.11.mlp.experts.down_proj": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.11.mlp.gate.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.12.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.12.mlp.experts.down_proj": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.12.mlp.gate.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.13.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.13.mlp.experts.down_proj": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.13.mlp.gate.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.14.mlp.experts.down_proj": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.14.mlp.gate.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.15.input_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.15.mlp.experts.down_proj": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.15.mlp.gate.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
|
||||
"model.language_model.layers.16.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.16.mlp.experts.down_proj": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.16.mlp.gate.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.17.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.17.mlp.experts.down_proj": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.17.mlp.gate.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.18.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.18.mlp.experts.down_proj": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.18.mlp.gate.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.19.input_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.19.mlp.experts.down_proj": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.19.mlp.gate.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
|
||||
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.2.mlp.experts.down_proj": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.2.mlp.gate.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.20.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.20.mlp.experts.down_proj": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.20.mlp.gate.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.21.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.21.mlp.experts.down_proj": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.21.mlp.gate.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.22.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.22.mlp.experts.down_proj": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.22.mlp.gate.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.23.input_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.23.mlp.experts.down_proj": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.23.mlp.gate.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
|
||||
"model.language_model.layers.24.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.24.mlp.experts.down_proj": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.24.mlp.gate.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.25.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.25.mlp.experts.down_proj": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.25.mlp.gate.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.26.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.26.mlp.experts.down_proj": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.26.mlp.gate.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.27.input_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.27.mlp.experts.down_proj": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.27.mlp.gate.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
|
||||
"model.language_model.layers.28.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.28.mlp.experts.down_proj": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.28.mlp.gate.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.29.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.29.mlp.experts.down_proj": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.29.mlp.gate.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.3.mlp.experts.down_proj": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.3.mlp.gate.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
|
||||
"model.language_model.layers.30.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.30.mlp.experts.down_proj": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.30.mlp.gate.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.31.input_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.31.mlp.experts.down_proj": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.31.mlp.gate.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
|
||||
"model.language_model.layers.32.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.32.mlp.experts.down_proj": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.32.mlp.gate.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.33.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.33.mlp.experts.down_proj": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.33.mlp.gate.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.34.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.34.mlp.experts.down_proj": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.34.mlp.gate.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.35.input_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.35.mlp.experts.down_proj": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.35.mlp.gate.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
|
||||
"model.language_model.layers.36.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.36.mlp.experts.down_proj": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.36.mlp.gate.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.36.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.36.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.36.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.36.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.36.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.36.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.36.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.37.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.37.mlp.experts.down_proj": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.37.mlp.gate.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.37.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.37.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.37.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.37.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.37.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.37.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.37.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.38.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.38.mlp.experts.down_proj": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.38.mlp.gate.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.38.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.38.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.38.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.38.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.38.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.38.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.38.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.39.input_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.39.mlp.experts.down_proj": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.39.mlp.gate.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.39.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.39.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.39.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.39.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.39.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.39.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.39.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
|
||||
"model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.4.mlp.experts.down_proj": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.4.mlp.gate.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.40.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.40.mlp.experts.down_proj": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.40.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.40.mlp.gate.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.40.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.40.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.40.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.40.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.40.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.40.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.40.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.41.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.41.mlp.experts.down_proj": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.41.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.41.mlp.gate.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.41.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.41.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.41.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.41.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.41.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.41.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.41.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.42.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.42.mlp.experts.down_proj": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.42.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.42.mlp.gate.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.42.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.42.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.42.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.42.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.42.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.42.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.42.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.43.input_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.43.mlp.experts.down_proj": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.43.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.43.mlp.gate.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.43.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.43.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.43.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.43.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.43.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.43.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.43.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
|
||||
"model.language_model.layers.44.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.44.mlp.experts.down_proj": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.44.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.44.mlp.gate.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.44.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.44.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.44.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.44.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.44.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.44.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.44.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.45.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.45.mlp.experts.down_proj": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.45.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.45.mlp.gate.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.45.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.45.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.45.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.45.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.45.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.45.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.45.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.46.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.46.mlp.experts.down_proj": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.46.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.46.mlp.gate.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.46.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.46.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.46.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.46.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.46.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.46.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.46.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.47.input_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.47.mlp.experts.down_proj": "model-00013-of-00013.safetensors",
|
||||
"model.language_model.layers.47.mlp.experts.gate_up_proj": "model-00013-of-00013.safetensors",
|
||||
"model.language_model.layers.47.mlp.gate.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.47.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.47.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.47.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.47.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.47.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.47.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.47.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
|
||||
"model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.5.mlp.experts.down_proj": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.5.mlp.gate.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.6.mlp.experts.down_proj": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.6.mlp.gate.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.7.mlp.experts.down_proj": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.7.mlp.gate.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
|
||||
"model.language_model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.8.mlp.experts.down_proj": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.8.mlp.gate.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.9.mlp.experts.down_proj": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.9.mlp.gate.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
|
||||
"model.language_model.norm.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.0.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.1.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.10.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.11.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.12.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.13.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.14.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.15.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.16.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.17.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.18.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.19.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.2.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.20.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.21.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.22.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.23.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.24.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.25.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.26.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.3.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.4.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.5.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.6.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.7.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.8.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.attn.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.attn.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.attn.qkv.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.attn.qkv.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.norm1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.norm1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.norm2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.blocks.9.norm2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.norm.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.0.norm.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.norm.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.1.norm.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.norm.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.deepstack_merger_list.2.norm.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.merger.linear_fc1.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.merger.linear_fc1.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.merger.linear_fc2.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.merger.linear_fc2.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.merger.norm.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.merger.norm.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.patch_embed.proj.bias": "model-00013-of-00013.safetensors",
|
||||
"model.visual.patch_embed.proj.weight": "model-00013-of-00013.safetensors",
|
||||
"model.visual.pos_embed.weight": "model-00013-of-00013.safetensors"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"disable_grouping": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_pad": null,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_processor_type": "Qwen2VLImageProcessorFast",
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_pixels": null,
|
||||
"merge_size": 2,
|
||||
"min_pixels": null,
|
||||
"pad_size": null,
|
||||
"patch_size": 16,
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_tensors": null,
|
||||
"size": {
|
||||
"longest_edge": 16777216,
|
||||
"shortest_edge": 65536
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
}
|
||||
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"crop_size": null,
|
||||
"data_format": "channels_first",
|
||||
"default_to_square": true,
|
||||
"device": null,
|
||||
"do_center_crop": null,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"do_sample_frames": true,
|
||||
"fps": 2,
|
||||
"image_mean": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"image_std": [
|
||||
0.5,
|
||||
0.5,
|
||||
0.5
|
||||
],
|
||||
"input_data_format": null,
|
||||
"max_frames": 768,
|
||||
"merge_size": 2,
|
||||
"min_frames": 4,
|
||||
"num_frames": null,
|
||||
"pad_size": null,
|
||||
"patch_size": 16,
|
||||
"processor_class": "Qwen3VLProcessor",
|
||||
"resample": 3,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"return_metadata": false,
|
||||
"size": {
|
||||
"longest_edge": 25165824,
|
||||
"shortest_edge": 4096
|
||||
},
|
||||
"temporal_patch_size": 2,
|
||||
"video_metadata": null,
|
||||
"video_processor_type": "Qwen3VLVideoProcessor"
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user