Add files using upload-large-folder tool

config.json

@@ -0,0 +1,56 @@
+{
+  "architectures": [
+    "LLaDA2MoeModelLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_llada2_moe.LLaDA2MoeConfig",
+    "AutoModel": "modeling_llada2_moe.LLaDA2MoeModel",
+    "AutoModelForCausalLM": "modeling_llada2_moe.LLaDA2MoeModelLM"
+  },
+  "dtype": "bfloat16",
+  "embedding_dropout": 0.0,
+  "first_k_dense_replace": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "llada2_moe",
+  "moe_intermediate_size": 512,
+  "moe_router_enable_expert_bias": true,
+  "n_group": 8,
+  "norm_head": false,
+  "norm_softmax": false,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts": 256,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 20,
+  "num_key_value_heads": 4,
+  "num_shared_experts": 1,
+  "output_dropout": 0.0,
+  "output_router_logits": false,
+  "pad_token_id": 156892,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 600000,
+  "rotary_dim": 64,
+  "routed_scaling_factor": 2.5,
+  "router_dtype": "fp32",
+  "score_function": "sigmoid",
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "topk_group": 4,
+  "transformers_version": "4.57.1",
+  "use_bias": false,
+  "use_cache": false,
+  "use_qkv_bias": false,
+  "use_rmsnorm": true,
+  "use_sliding_window": false,
+  "using_split_qkv_in_self_attention": false,
+  "vocab_size": 157184
+}

configuration_llada2_moe.py

@@ -0,0 +1,85 @@
+"""LLaDA2 MoE model configuration"""
+
+from transformers.configuration_utils import PretrainedConfig
+
+
+class LLaDA2MoeConfig(PretrainedConfig):
+    model_type = "llada2_moe"
+
+    def __init__(
+        self,
+        vocab_size=30592,
+        hidden_size=1024,
+        intermediate_size=None,
+        num_hidden_layers=24,
+        num_attention_heads=16,
+        num_key_value_heads=0,
+        hidden_act="silu",
+        use_qkv_bias=False,  # llada2 only
+        use_qk_norm=False,
+        use_bias=True,  # llada2 only
+        rms_norm_eps=1e-05,
+        norm_head=False,  # llada2 only
+        tie_word_embeddings=False,  # PretrainedConfig key, here change default value.
+        embedding_dropout=0.1,
+        attention_dropout=0.1,
+        output_dropout=0.1,
+        initializer_range=0.02,
+        max_position_embeddings=16384,
+        rope_theta=10000.0,
+        use_cache=True,
+        use_sliding_window=False,
+        sliding_window=4096,
+        max_window_layers=28,
+        rope_scaling=None,
+        pad_token_id=126081,
+        num_experts=16,
+        num_shared_experts=0,
+        num_experts_per_tok=2,
+        n_group=8,
+        topk_group=4,
+        routed_scaling_factor=2.5,
+        moe_intermediate_size=None,
+        first_k_dense_replace=0,
+        head_dim=None,
+        output_router_logits=False,
+        partial_rotary_factor=0.5,
+        **kwargs,
+    ):
+        self.num_hidden_layers = num_hidden_layers
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.intermediate_size = intermediate_size
+        self.num_attention_heads = num_attention_heads
+        self.num_key_value_heads = num_key_value_heads
+        self.hidden_act = hidden_act
+        self.use_qkv_bias = use_qkv_bias
+        self.use_bias = use_bias
+        self.norm_head = norm_head
+        self.rms_norm_eps = rms_norm_eps
+        self.embedding_dropout = embedding_dropout
+        self.attention_dropout = attention_dropout
+        self.output_dropout = output_dropout
+        self.initializer_range = initializer_range
+        self.max_position_embeddings = max_position_embeddings
+        self.rope_theta = rope_theta
+        self.use_cache = use_cache
+        self.use_sliding_window = use_sliding_window
+        self.sliding_window = sliding_window
+        self.max_window_layers = max_window_layers
+        self.head_dim = head_dim or self.hidden_size // self.num_attention_heads
+        self.rope_scaling = rope_scaling
+
+        # MoE configs
+        self.num_experts = num_experts
+        self.num_shared_experts = num_shared_experts
+        self.num_experts_per_tok = num_experts_per_tok
+        self.n_group = n_group
+        self.topk_group = topk_group
+        self.moe_intermediate_size = moe_intermediate_size
+        self.first_k_dense_replace = first_k_dense_replace
+        self.output_router_logits = output_router_logits
+        self.routed_scaling_factor = routed_scaling_factor
+        self.partial_rotary_factor = partial_rotary_factor
+
+        super().__init__(pad_token_id=pad_token_id, tie_word_embeddings=tie_word_embeddings, **kwargs)

model-00000-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21a904092ad20835b30400a1ee939f765d88214381e0256f1a5b598da9b425cc
+size 5735111000

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f89a9d7bffaa06dffee29ecca93c870657ae670cb9a848c052adeb84487f4df
+size 3825430152

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:441c1b58669f0cabc1c6f22ab83a56f8c2e38eba2a2e534d01257d7c8247695a
+size 3825430152

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602798afb9acfccefe5f2186a59ee24b4847f3f587f3fa589173f02fc917c4a6
+size 3825431744

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bd5fc04fc64bc8ef9e54dbbb630c570417dc45ee2bbd47b0d71dffc61830ccf
+size 3825431976

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b097875ab571ecfb710cecb3cacb46b4de67a88b5eacdf8942a8133384e03a
+size 3825431976

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d77a97241a25a79c973aaed3395eb21f8c940e40da71a1279ae19ea8431ba5ee
+size 3825431976

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f8f4a0c54780d41250b9265075169971f2e4fe6b52f4ccd766ddd2305bc764
+size 3825431976

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<|startoftext|>",
+  "cls_token": "[CLS]",
+  "eos_token": "<|endoftext|>",
+  "gmask_token": "[gMASK]",
+  "pad_token": "<|endoftext|>",
+  "mask_token": "<|mask|>"
+}

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{% set thinking_option = 'off' %}\n{{- '<role>SYSTEM</role>' }}\n{%- if messages[0].role == 'system' %}\n    {{- messages[0].content + '\\n' }}\n{%- endif %}\n{%- if tools %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call>\\n\" }}\n{%- endif %}\n{{- 'detailed thinking ' + thinking_option + '<|role_end|>' }}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if message.role == \"user\" %}\n        {{- '<role>HUMAN</role>' + message.content + '<|role_end|>' }}\n    {%- elif message.role == \"system\" and not loop.first %}\n        {{- '<role>SYSTEM</role>' + message.content + '<|role_end|>' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if reasoning_content %}\n                {{- '<role>ASSISTANT</role>' + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<role>ASSISTANT</role>' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<role>ASSISTANT</role>' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|role_end|>' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<role>OBSERVATION</role>' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|role_end|>' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<role>ASSISTANT</role>' }}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "eos_token": "<|endoftext|>",
+  "mask_token": "<|mask|>",
+  "fast_tokenizer": true,
+  "gmask_token": "[gMASK]",
+  "merges_file": null,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "trust_remote_code": true,
+  "vocab_file": null
+}