Add SO-101 Edge single-object policy iter 1500 (from iter 6500, merged + exported)

.gitattributes

@@ -38,3 +38,4 @@ iter_6500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 iter_7000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 single_bin_from6500/iter_500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 single_bin_from6500/iter_1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+single_bin_from6500/iter_1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text

single_bin_from6500/iter_1500/chat_template.jinja

@@ -0,0 +1,324 @@
+
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '
+<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'
+<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+{%- set enable_thinking = enable_thinking if enable_thinking is defined else True %}
+{%- set truncate_history_thinking = truncate_history_thinking if truncate_history_thinking is defined else True %}
+
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- set loop_messages = messages %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- if messages[0]["content"] is string %}
+        {%- set system_message = messages[0]["content"] %}
+    {%- else %}
+        {%- set ns = namespace(system_text="") %}
+        {%- for part in messages[0]["content"] %}
+            {%- if 'text' in part %}
+                {%- set ns.system_text = ns.system_text + part.text %}
+            {%- endif %}
+        {%- endfor %}
+        {%- set system_message = ns.system_text %}
+    {%- endif %}
+
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+{# Recompute last_user_idx relative to loop_messages after handling system #}
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+{%- if system_message is defined %}
+    {{- "<|im_start|>system
+" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system
+" }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {%- if system_message is defined and system_message | length > 0 %}
+        {{- "
+
+" }}
+    {%- endif %}
+    {{- "# Tools
+
+You have access to the following functions:
+
+" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "
+<function>
+<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '
+<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '
+<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '
+<parameter>' }}
+                {{- '
+<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '
+<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '
+<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- if param_fields.enum is defined %}
+                    {{- '
+<enum>' ~ (param_fields.enum | tojson | safe) ~ '</enum>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description', 'enum'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '
+</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties', 'required'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {%- if tool.parameters is defined and tool.parameters.required is defined %}
+            {{- '
+<required>' ~ (tool.parameters.required | tojson | safe) ~ '</required>' }}
+        {%- endif %}
+        {{- '
+</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '
+</function>' }}
+    {%- endfor %}
+    {{- "
+</tools>" }}
+
+    {{- '
+
+If you choose to call a function ONLY reply in the following format with NO suffix:
+
+<tool_call>
+<function=example_function_name>
+<parameter=example_parameter_1>
+value_1
+</parameter>
+<parameter=example_parameter_2>
+This is the value for the second parameter
+that can span
+multiple lines
+</parameter>
+</function>
+</tool_call>
+
+<IMPORTANT>
+Reminder:
+- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags
+- Required parameters MUST be specified
+- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after
+- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls
+</IMPORTANT>' }}
+{%- endif %}
+
+
+{%- if system_message is defined %}
+    {{- '<|im_end|>
+' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>
+' }}
+    {%- endif %}
+{%- endif %}
+
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" %}
+        {# Add reasoning content in to content field for unified processing below. #}
+        {%- set text_content = namespace(text_content="") -%}
+        {%- if message.content is string %}
+            {%- set text_content.text_content = message.content %}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if 'text' in content %}
+                    {%- set text_content.text_content = content.text %}
+                    {%- break %}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
+            {%- set content = "<think>
+" ~ message.reasoning_content ~ "
+</think>
+" ~ (text_content.text_content | default('', true)) %}
+        {%- else %}
+            {%- set content = text_content.text_content | default('', true) %}
+            {# Allow downstream logic to to take care of broken thought, only handle coherent reasoning here. #}
+            {%- if '<think>' not in content and '</think>' not in content %}
+                {%- set content = "<think></think>" ~ content %}
+            {%- else %}
+                {%- set content = content %}
+            {%- endif -%}
+        {%- endif %}
+        {%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+            {# Assistant message has tool calls. #}
+            {{- '<|im_start|>assistant
+' }}
+                {%- set include_content = not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {%- if content is string and content | trim | length > 0 %}
+                    {%- if include_content %}
+                        {{- (content | trim) ~ '
+' -}}
+                    {%- else %}
+                        {%- set c = (content | string) %}
+                        {%- if '</think>' in c %}
+                            {# Keep only content after the last closing think. Also generation prompt causes this. #}
+                            {%- set c = c.split('</think>')[-1] %}
+                        {%- elif '<think>' in c %}
+                            {# If <think> was opened but never closed, drop the trailing think segment #}
+                            {%- set c = c.split('<think>')[0] %}
+                        {%- endif %}
+                        {%- set c = "<think></think>" ~ c | trim %}
+                        {%- if c | length > 0 %}
+                            {{- c ~ '
+' -}}
+                        {%- endif %}
+                    {%- endif %}
+                {%- else %}
+                    {{- "<think></think>" -}}
+                {%- endif %}
+                {%- for tool_call in message.tool_calls %}
+                    {%- if tool_call.function is defined %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {{- '<tool_call>
+<function=' ~ tool_call.name ~ '>
+' -}}
+                        {%- if tool_call.arguments is defined %}
+                            {%- for args_name, args_value in tool_call.arguments|items %}
+                                {{- '<parameter=' ~ args_name ~ '>
+' -}}
+                                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                                {{- args_value ~ '
+</parameter>
+' -}}
+                            {%- endfor %}
+                        {%- endif %}
+                    {{- '</function>
+</tool_call>
+' -}}
+                {%- endfor %}
+                {{- '<|im_end|>
+' }}
+        {%- else %}
+            {# Assistant message doesn't have tool calls. #}
+            {%- if not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {{- '<|im_start|>assistant
+' ~ (content | default('', true) | string | trim) ~ '<|im_end|>
+' }}
+            {%- else %}
+                {%- set c = (content | default('', true) | string) %}
+                {%- if '<think>' in c and '</think>' in c %}
+                    {%- set c = "<think></think>" ~ c.split('</think>')[-1] %}
+                {%- endif %}
+                {%- set c = c | trim %}
+                {%- if c | length > 0 %}
+                    {{- '<|im_start|>assistant
+' ~ c ~ '<|im_end|>
+' }}
+                {%- else %}
+                    {{- '<|im_start|>assistant
+<|im_end|>
+' }}
+                {%- endif %}
+            {%- endif %}
+        {%- endif %}
+    {%- elif message.role == "user" or message.role == "system" %}
+        {{- '<|im_start|>' + message.role + '
+' }}
+        {%- 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|>
+' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user
+' }}
+        {%- endif %}
+        {{- '<tool_response>
+' }}
+        {{- message.content }}
+        {{- '
+</tool_response>
+' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>
+' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>
+' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '
+' + message.content + '<|im_end|>
+' }}
+    {%- endif %}
+{%- endfor %}
+
+{%- if add_generation_prompt %}
+    {%- if enable_thinking %}
+        {{- '<|im_start|>assistant
+<think>
+' }}
+    {%- else %}
+        {{- '<|im_start|>assistant
+<think></think>' }}
+    {%- endif %}
+{%- endif %}

single_bin_from6500/iter_1500/checkpoint.json

@@ -0,0 +1,24 @@
+{
+  "checkpoint_cache_dir": null,
+  "checkpoint_hf": null,
+  "checkpoint_path": "/home/zeux/cosmos-framework/outputs/train/cosmos3_action/action_sft_sim/action_policy_so101_edge_single_bin_from6500/checkpoints/iter_000001500_merged/model",
+  "checkpoint_type": "dcp",
+  "config_file": "cosmos_framework/configs/base/config.py",
+  "config_file_type": "module",
+  "credential_path": "credentials/gcp_checkpoint.secret",
+  "experiment": "action_policy_so101_edge_single_bin",
+  "experiment_overrides": [
+    "model.config.diffusion_expert_config.load_weights_from_pretrained=False",
+    "model.config.vlm_config.pretrained_weights.enabled=False",
+    "checkpoint.load_from_object_store.enabled=False",
+    "model.config.ema.enabled=false"
+  ],
+  "model_memory_bytes": null,
+  "policy": {
+    "action_chunk_size": 32,
+    "conditioning_fps": 30.0,
+    "domain_name": "so101"
+  },
+  "use_ema_weights": false,
+  "vlm_processor_from_checkpoint": false
+}

single_bin_from6500/iter_1500/config.json

@@ -0,0 +1,196 @@
+{
+  "architectures": [
+    "Cosmos3OmniModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "cosmos3.model.Cosmos3OmniConfig",
+    "AutoModel": "cosmos3.model.Cosmos3OmniModel"
+  },
+  "dtype": "bfloat16",
+  "model": {
+    "_recursive_": false,
+    "_target": "omni_mot_model",
+    "config": {
+      "_type": "omni_mot_model_config",
+      "action_gen": true,
+      "activation_checkpointing": {
+        "_type": "activation_checkpointing_config",
+        "determinism_check": "default",
+        "mode": "full",
+        "preserve_rng_state": true,
+        "save_ops_regex": [
+          "fmha"
+        ]
+      },
+      "causal_training_strategy": "none",
+      "compile": {
+        "_type": "compile_config",
+        "ar_post_saturation_mode": "default",
+        "compile_dynamic": true,
+        "compiled_region": "language",
+        "coordinate_descent_tuning": false,
+        "enabled": false,
+        "max_autotune_pointwise": false,
+        "use_cuda_graphs": false
+      },
+      "diffusion_expert_config": {
+        "_type": "diffusion_expert_config",
+        "base_fps": 24,
+        "enable_fps_modulation": true,
+        "load_weights_from_pretrained": false,
+        "max_vae_latent_side_after_patchify": 20,
+        "patch_spatial": 2,
+        "sound_base_temporal_compression_factor": null,
+        "timestep_range": 1.0,
+        "unified_3d_mrope_reset_spatial_ids": true,
+        "unified_3d_mrope_temporal_modality_margin": 15000,
+        "vision_temporal_position_mode": "latent_index"
+      },
+      "ema": {
+        "_type": "ema_config",
+        "enabled": false,
+        "iteration_shift": 0,
+        "rate": 0.1
+      },
+      "enable_input_bias": true,
+      "exclude_reasoner_weights_from_checkpoint": false,
+      "fixed_step_sampler_config": null,
+      "input_caption_key": "ai_caption",
+      "input_image_key": "images",
+      "input_video_key": "video",
+      "joint_attn_implementation": "two_way",
+      "latent_downsample_factor": 16,
+      "lbl": {
+        "_type": "lbl_config",
+        "coeff_gen": null,
+        "coeff_und": null,
+        "method": "local"
+      },
+      "load_vision_tokenizer": true,
+      "log_enc_time_every_n": 100,
+      "lora_alpha": 32,
+      "lora_enabled": false,
+      "lora_extra_trainable": "",
+      "lora_rank": 16,
+      "lora_target_modules": "q_proj_moe_gen,k_proj_moe_gen,v_proj_moe_gen,o_proj_moe_gen",
+      "max_action_dim": 64,
+      "max_num_tokens_after_packing": 45056,
+      "natten_parameter_list": null,
+      "net": null,
+      "num_embodiment_domains": 32,
+      "parallelism": {
+        "_type": "parallelism_config",
+        "attention_io_layout": "sequence_sharded",
+        "cfg_parallel_shard_degree": 1,
+        "context_parallel_shard_degree": 1,
+        "data_parallel_replicate_degree": 1,
+        "data_parallel_shard_degree": 8,
+        "enable_inference_mode": false,
+        "fsdp_master_dtype": "float32"
+      },
+      "precision": "bfloat16",
+      "rectified_flow_inference_config": {
+        "_type": "rectified_flow_inference_config",
+        "num_train_timesteps": 1000,
+        "scheduler_type": "unipc",
+        "shift": 1,
+        "use_dynamic_shifting": false
+      },
+      "rectified_flow_training_config": {
+        "_type": "rectified_flow_training_config",
+        "action_loss_weight": 10.0,
+        "image_loss_scale": null,
+        "independent_action_schedule": false,
+        "independent_sound_schedule": false,
+        "loss_scale": 10.0,
+        "normalize_loss_by_active": false,
+        "shift": {
+          "256": 3,
+          "480": 5,
+          "720": 10
+        },
+        "shift_action": null,
+        "shift_sound": null,
+        "sound_loss_scale": 2.0,
+        "train_time_action_distribution": "logitnormal",
+        "train_time_image_distribution": "logitnormal",
+        "train_time_sound_distribution": "logitnormal",
+        "train_time_video_distribution": "waver",
+        "train_time_weight": "uniform",
+        "use_discrete_rf": false,
+        "use_dynamic_shift": false
+      },
+      "resolution": "480",
+      "sound_dim": null,
+      "sound_gen": false,
+      "sound_latent_fps": 25,
+      "sound_tokenizer": null,
+      "state_ch": 48,
+      "state_t": 300,
+      "tokenizer": {
+        "_target": "wan2pt2_vae_interface",
+        "bucket_name": "",
+        "causal": true,
+        "chunk_duration": 93,
+        "encode_bucket_multiple": null,
+        "encode_chunk_frames": {
+          "256": 68,
+          "480": 24,
+          "720": 8,
+          "768": 8
+        },
+        "encode_exact_durations": null,
+        "keep_decoder_cache": false,
+        "object_store_credential_path_pretrained": "",
+        "spatial_compression_factor": 16,
+        "temporal_compression_factor": 4,
+        "temporal_window": null,
+        "use_streaming_encode": false,
+        "vae_path": "pretrained/tokenizers/video/wan2pt2/Wan2.2_VAE.pth"
+      },
+      "video_temporal_causal": false,
+      "vision_gen": true,
+      "vlm_config": {
+        "_type": "vlm_config",
+        "layer_module": null,
+        "model_instance": {
+          "_target": "nemotron3_dense_vl_text_for_causal_lm",
+          "config": {
+            "_target": "create_vlm_config",
+            "base_config": {
+              "_target": "nemotron3_dense_vl_mot_config_from_json_file",
+              "json_file": "cosmos3://vfm/models/vlm/nemotron_3_dense_vl/configs/Nemotron-2B-Dense-VL.json"
+            },
+            "freeze_und": false,
+            "include_visual": null,
+            "layer_module": "MoTDecoderLayer",
+            "qk_norm_for_text": false,
+            "tie_word_embeddings": true,
+            "use_und_k_norm_for_gen": true
+          }
+        },
+        "model_name": "nvidia/Cosmos3-Edge-Reasoner",
+        "pretrained_weights": {
+          "_type": "pretrained_weights_config",
+          "backbone_path": "s3://bucket/cosmos3/pretrained/huggingface/nvidia/Cosmos3-Edge-Reasoner-590c1c0/",
+          "checkpoint_format": null,
+          "credentials_path": "",
+          "enable_gcs_patch_in_boto3": true,
+          "enabled": false
+        },
+        "qk_norm": false,
+        "safetensors_path": "",
+        "tie_word_embeddings": false,
+        "tokenizer": {
+          "_target": "build_processor_lazy",
+          "repository": "nvidia/Cosmos3-Edge",
+          "revision": "main",
+          "subdir": ""
+        },
+        "use_system_prompt": false
+      }
+    }
+  },
+  "model_type": "cosmos3_omni",
+  "transformers_version": "4.57.6"
+}

single_bin_from6500/iter_1500/export_manifest.json

@@ -0,0 +1,20 @@
+{
+  "export_args": {
+    "config_only": false,
+    "student_only_checkpoint_metadata": false,
+    "verify": false,
+    "vit": true,
+    "vit_checkpoint_path": null
+  },
+  "framework_commit": "5e67049cd94acb667786f1e6dd0dab821cb90c97",
+  "processor_source": {
+    "bundled": true,
+    "repo": "nvidia/Cosmos3-Edge",
+    "revision": "344d602b128d1bbdacb43b08d0a3626f46343e29"
+  },
+  "vision_tower_source": {
+    "bundled": true,
+    "repo": "nvidia/Cosmos3-Edge",
+    "revision": "344d602b128d1bbdacb43b08d0a3626f46343e29"
+  }
+}

single_bin_from6500/iter_1500/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dade6327f71e97eb271baaf87da485e80ce79d59d892b64ecb49a5f55a5f433
+size 5000054640

single_bin_from6500/iter_1500/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fdba6bbde3a788b7aed452d577036823ac29279c61fd9aae91013257a6182a
+size 1739338512

single_bin_from6500/iter_1500/model.safetensors.index.json

@@ -0,0 +1,557 @@
+{
+  "metadata": {
+    "total_parameters": 3369657024,
+    "total_size": 6739314048
+  },
+  "weight_map": {
+    "model.net.action2llm.bias.weight": "model-00002-of-00002.safetensors",
+    "model.net.action2llm.fc.weight": "model-00002-of-00002.safetensors",
+    "model.net.action_modality_embed": "model-00001-of-00002.safetensors",
+    "model.net.language_model.lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.0.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.1.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.10.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.11.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.12.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.13.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.14.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.15.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.16.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.17.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.18.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.19.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.2.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.20.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.21.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.input_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.mlp_moe_gen.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.mlp_moe_gen.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.post_attention_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.self_attn.k_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.self_attn.o_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.22.self_attn.v_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.input_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.mlp_moe_gen.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.mlp_moe_gen.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.post_attention_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.self_attn.k_norm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.self_attn.k_norm_und_for_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.self_attn.k_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.self_attn.o_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.self_attn.q_norm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.self_attn.q_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.23.self_attn.v_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.input_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.mlp_moe_gen.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.mlp_moe_gen.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.post_attention_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.self_attn.k_norm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.self_attn.k_norm_und_for_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.self_attn.k_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.self_attn.o_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.self_attn.q_norm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.self_attn.q_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.24.self_attn.v_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.input_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.mlp_moe_gen.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.mlp_moe_gen.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.post_attention_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.self_attn.k_norm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.self_attn.k_norm_und_for_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.self_attn.k_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.self_attn.o_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.self_attn.q_norm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.self_attn.q_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.25.self_attn.v_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.input_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.mlp_moe_gen.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.mlp_moe_gen.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.post_attention_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.self_attn.k_norm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.self_attn.k_norm_und_for_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.self_attn.k_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.self_attn.o_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.self_attn.q_norm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.self_attn.q_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.26.self_attn.v_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.input_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.mlp_moe_gen.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.mlp_moe_gen.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.post_attention_layernorm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.self_attn.k_norm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.self_attn.k_norm_und_for_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.self_attn.k_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.self_attn.o_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.self_attn.q_norm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.self_attn.q_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.27.self_attn.v_proj_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.3.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.4.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.5.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.6.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.7.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.8.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.input_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.mlp_moe_gen.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.mlp_moe_gen.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.post_attention_layernorm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.self_attn.k_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.self_attn.k_norm_und_for_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.self_attn.k_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.self_attn.o_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.self_attn.q_norm_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.self_attn.q_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.layers.9.self_attn.v_proj_moe_gen.weight": "model-00001-of-00002.safetensors",
+    "model.net.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.net.language_model.model.norm_moe_gen.weight": "model-00002-of-00002.safetensors",
+    "model.net.llm2action.bias.weight": "model-00002-of-00002.safetensors",
+    "model.net.llm2action.fc.weight": "model-00002-of-00002.safetensors",
+    "model.net.llm2vae.bias": "model-00002-of-00002.safetensors",
+    "model.net.llm2vae.weight": "model-00002-of-00002.safetensors",
+    "model.net.time_embedder.mlp.0.bias": "model-00002-of-00002.safetensors",
+    "model.net.time_embedder.mlp.0.weight": "model-00002-of-00002.safetensors",
+    "model.net.time_embedder.mlp.2.bias": "model-00002-of-00002.safetensors",
+    "model.net.time_embedder.mlp.2.weight": "model-00002-of-00002.safetensors",
+    "model.net.vae2llm.bias": "model-00002-of-00002.safetensors",
+    "model.net.vae2llm.weight": "model-00002-of-00002.safetensors"
+  }
+}

single_bin_from6500/iter_1500/preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Cosmos3EdgeImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "merge_size": 2,
+  "patch_size": 16,
+  "processor_class": "Cosmos3EdgeProcessor",
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  }
+}

single_bin_from6500/iter_1500/processor_config.json

@@ -0,0 +1,46 @@
+{
+  "image_processor": {
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Cosmos3EdgeImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "processor_class": "Cosmos3EdgeProcessor",
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    }
+  },
+  "processor_class": "Cosmos3EdgeProcessor",
+  "video_processor": {
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "processor_class": "Cosmos3EdgeProcessor",
+    "return_metadata": true,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 1,
+    "video_processor_type": "Cosmos3EdgeVideoProcessor"
+  }
+}

single_bin_from6500/iter_1500/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

single_bin_from6500/iter_1500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc692a99dca6d92a44e9529ffb53541eb79bb260eec7281bc51268c05d7311c
+size 17077500

single_bin_from6500/iter_1500/video_preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "merge_size": 2,
+  "patch_size": 16,
+  "processor_class": "Cosmos3EdgeProcessor",
+  "return_metadata": true,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 1,
+  "video_processor_type": "Cosmos3EdgeVideoProcessor"
+}

single_bin_from6500/iter_1500/vision_encoder/config.json

@@ -0,0 +1,27 @@
+{
+  "image_token_id": 19,
+  "projector_config": {
+    "input_hidden_size": 1152,
+    "merger_intermediate_size": 11520,
+    "model_type": "cosmos3_edge_projector",
+    "out_hidden_size": 2048,
+    "spatial_merge_size": 2,
+    "use_postshuffle_norm": false
+  },
+  "video_token_id": 18,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "cosmos3_edge_vision",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "num_patches": 256,
+    "patch_size": 16,
+    "spatial_merge_size": 2
+  },
+  "vision_start_token_id": 20
+}

single_bin_from6500/iter_1500/vision_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2180ad739ecc96b5c1e9386892d3c5c08bfa42b9cdab9aabc53b028671db89b3
+size 978739880