Upload MCP-transformer pretrain checkpoints

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/chat_template.jinja

@@ -0,0 +1,145 @@
+{%- if enable_thinking is not defined -%}
+    {%- set enable_thinking = false -%}
+{%- endif -%}
+{%- macro render_content(content, is_system_content=false) -%}
+    {%- if content is string -%}
+        {{- content -}}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- set ns = namespace(parts=[]) -%}
+        {%- for item in content -%}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' -%}
+                {%- if is_system_content -%}
+                    {{- raise_exception('System message cannot contain images.') -}}
+                {%- endif -%}
+                {%- set ns.parts = ns.parts + ['<|image_pad|>'] -%}
+            {%- elif 'video' in item or item.type == 'video' -%}
+                {%- if is_system_content -%}
+                    {{- raise_exception('System message cannot contain videos.') -}}
+                {%- endif -%}
+                {%- set ns.parts = ns.parts + ['<|video_pad|>'] -%}
+            {%- elif 'text' in item -%}
+                {%- set ns.parts = ns.parts + [item.text] -%}
+            {%- else -%}
+                {{- raise_exception('Unexpected item type in content.') -}}
+            {%- endif -%}
+        {%- endfor -%}
+        {{- ns.parts | join('\n') -}}
+    {%- elif content is none or content is undefined -%}
+        {{- '' -}}
+    {%- else -%}
+        {{- raise_exception('Unexpected content type.') -}}
+    {%- endif -%}
+{%- endmacro -%}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/config.json

@@ -0,0 +1,122 @@
+{
+  "architectures": [
+    "mobileoMiniSFTForCausalLM"
+  ],
+  "bos_token_id": 248045,
+  "diffusion_name_or_path": "Efficient-Large-Model/Sana_600M_512px_diffusers",
+  "downsample_mode": "16x",
+  "drop_vision_last_layer": false,
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "freeze_dit": false,
+  "freeze_mm_mlp_adapter": false,
+  "image_aspect_ratio": "pad",
+  "image_size": 1120,
+  "image_token_id": 248056,
+  "insert_layer_id": 6,
+  "is_train": true,
+  "merge_kernel_size": [
+    2,
+    2
+  ],
+  "merger_times": 1,
+  "mm_projector_lr": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "model_type": "mobileo_minicpm",
+  "pad_token_id": 248044,
+  "patch_size": 14,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": null,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 3584,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 16,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 8,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 248094
+  },
+  "tie_word_embeddings": true,
+  "tokenizer_model_max_length": 512,
+  "tokenizer_padding_side": "right",
+  "transformers_version": "5.10.2",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": false,
+  "use_mm_proj": true,
+  "video_token_id": 248057,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 980,
+    "insert_layer_id": 6,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "minicpmv4_6_vision",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "window_kernel_size": [
+      2,
+      2
+    ]
+  },
+  "vlm_num_layers": 4
+}

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 248045,
+  "do_sample": true,
+  "eos_token_id": [
+    248046,
+    248044,
+    248046
+  ],
+  "pad_token_id": 248044,
+  "repetition_penalty": 1.0,
+  "temperature": 0.7,
+  "top_k": 0,
+  "top_p": 1.0,
+  "transformers_version": "5.10.2"
+}

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3727eafb4a77a6b0a19e32b990a84002f367652a0ea90d41c241c9f6ddd715dd
+size 225222279

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe0f5077bec2546e045200c6c59c518291e9f406a73e39330de8916619fca09
+size 225218329

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d277e3de7853d5e93f6b18d33179fb995871e8b54d2cc058b1c00cceeb0695
+size 225218329

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dde2f3ab2f4f020c97fe1a998b4d5b295d7bcad1c9f7f30ce33e3c32d6ac6e6
+size 225218521

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1419fdf4ecacd6a33e0fab78a010bdd7867ffc6e61b027bbd563cd4de466ace
+size 225218521

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d0b1c08b3205665a61adc77636c5f4d3e582e6340c297d8d917a929aa8445a
+size 225218585

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920159622df32e693b2e6656089f8b05f55dd0541f5f28bf1e60c24525c22e95
+size 225218521

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d34bf13f44ff4c076bbaa02e1b5de6b3602bbc1d012932d032113554c324fd
+size 225218457

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9bd3107b99e79cd4cd7c8af157d9963c3da698227013d950901fb8aaedcc818
+size 225218521

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e27ec90fa48c9fe7454bcb3cda970f97587ea255d966817a1476e7873d8cb652
+size 225218457

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9caecc85807f5241239ec2a2a13d593e426ef3a304948ff0e597b7faa7cfddc5
+size 225218457

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a90be67ba390a17e49fe9af74d7b70f558a1aeca166bef85da36f4b4a07286f7
+size 225218759

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b4db418bf726b26ba2056149f266c418f0647a893131212464d99599369d3d
+size 225218521

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f50d80f9427557e016ef273136bf474bce601ffb88a871775e8413d8825a2d72
+size 225218457

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892a26a0c1c40e4507e3e8055d9f35455cfc98607bb4c75bb0f19a1b0c85f4b4
+size 225218457

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad951db2c28b8839b8c875fd3d78e5632bf371442df3db3e1b7b0cedfa3b1009
+size 225218585

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c7c9bc98cfa569293ec0e8909d34ce7c23fd495d90088540ab25467b009f7d
+size 225218585

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb06b9410a619b523747d4558930209e1eb2834ec7be91ab7ec536eed6705b36
+size 225218585

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ae595db80bc386c4a1a06d8ffba2d536237237b5aacdf00cb24e9a6d4defff
+size 225218457

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48441c85ccf3be6116c5dc5fa249f69d3b5784e6b9a2299df08eda0e6d93272a
+size 225218393

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:393ba8fd3371dc0c8f2126966d3c7607cd7bf9bc61ecdab9de651098782d885c
+size 225218457

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:867e9881977c543499c5e88b917fd8d783a1c9cffbb480871b13380d8a6950e4
+size 225218329

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1704030b35bc5c07d092088b37dcf552a85aee79f2ce246da34cdc03754faf6a
+size 225218631

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2625821a2d745d969fce16638501825ffc799fc6d9f1f94e46743aa5e84b7a2f
+size 225218457

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb13b5bdd1aa8f08df6b6861cd662581529972fd3e5ea3074d89a82c811577f
+size 225218393

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ab463ed23ac6f4a146725a96b477bfc8580ad418e5b229bb6d914f3427b87b9
+size 225218567

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66f0d69f85f1f988d2ce296512367b12ec89bb4458a255bbabd967e7d37b12a
+size 225218503

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a8409d1eab1b9e4e4d9e494c1b81a350a46d1096403d3e7f6caf6857b5ecb7
+size 225218375

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44fa0d020a79c730a6105a2318cc548e35274fe4ba48d05317a209f65eeea72
+size 225218503

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b096a9496774c666396d103feb7384fe897dab3c5ac4c08df67b983cf4e4fd4
+size 225218311

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879fa3c3260e1092b5104e740863607c908d3d04efd171ff13f725ba346afd8d
+size 225218503

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5acaa9c262776541acff2dd084c2a66292d1fbc0230620bf1936d1a5057c08ac
+size 225218375

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/global_step10000/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1973adfaa1e2b1e46934b7e4257527b749e9fe4ef173a74a47b6674b198db435
+size 4427172165

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/latest

@@ -0,0 +1 @@
+global_step10000

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4ac38d5c5a64c925064b707b0257013973b96386526d2667a1e0f2ddc6a8c7
+size 4934801666

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b7a8929bd1142187d43e6f309ae76f93b1ef042878fa7e4d658ae1985854ec
+size 16389

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ea4209e2f4fdb254df10867b3e6e64a265a81c4c6092d77fd386a811347af8
+size 16389

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a4d8d97dca08793f874fd750a95df3c8b3b93e2e517d38239f4f9e720a73aa
+size 16404

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8ca2037c9e54dc6ab6df1a276018d34581f2ac25ab48b540faa9b2d99d6e90
+size 16404

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/rng_state_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ec827bd2e5f9094181fad99803b9473f0387fd9bf43ed9980f2e2ec1123652
+size 16404

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdd013945132a8e284a24035281db4d09a1cb2760d26f331d6007e556fe0db20
+size 16404

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad2671559d23be7dc8cc176f8bab3f95f879b9b3510e9f89f92058b9fca6f57
+size 16404

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/rng_state_15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71979114d249ed9ed4edc7484e5652232ccae4f1c1d3208dfeefa11f92e71d32
+size 16404

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/rng_state_16.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:824689b54ca7d9e3485c994423143c866cfd5af88896a138bea73358906dcb4c
+size 16404

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/rng_state_17.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78c5dfe3481873444f0b54ca5e3e5154807abfe017eabb3921b7aa7e4f7e4bc
+size 16404

Mobile-O-0.5B-Pretrain-minicpm_mcptf2/checkpoint-10000/rng_state_18.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddde9738d58dc33829dfe16f42fc9e702886fa5d07b046152ec35af37d4e0187
+size 16404