Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.jinja

@@ -0,0 +1,112 @@
+{%- macro render_content(msg) -%}
+    {%- set c = msg.get('content') -%}
+    {%- if c is string -%}
+      {{ c }}
+    {%- elif c is not none -%}
+      {% for content in c -%}
+        {% if content['type'] == 'image' or content['type'] == 'image_url' -%}
+          <|media_begin|>image<|media_content|><|media_pad|><|media_end|>
+        {% elif content['type'] == 'video' or content['type']== 'video_url'-%}
+          <|kimi_k25_video_placeholder|>
+        {% else -%}
+          {{ content['text'] }}
+        {%- endif -%}
+      {%- endfor -%}
+    {%- endif -%}
+{%- endmacro -%}
+
+{% macro set_roles(message) -%}
+  {%- set role_name =  message.get('name') or  message['role'] -%}
+  {%- if message['role'] == 'user' -%}
+    <|im_user|>{{role_name}}<|im_middle|>
+  {%- elif message['role'] == 'assistant' -%}
+    <|im_assistant|>{{role_name}}<|im_middle|>
+  {%- else -%}
+    <|im_system|>{{role_name}}<|im_middle|>
+  {%- endif -%}
+{%- endmacro -%}
+
+
+{%- macro render_toolcalls(message) -%}
+  <|tool_calls_section_begin|>
+  {%- for tool_call in message['tool_calls'] -%}
+    {%- set formatted_id = tool_call['id'] -%}
+    <|tool_call_begin|>{{ formatted_id }}<|tool_call_argument_begin|>{% if tool_call['function']['arguments'] is string %}{{ tool_call['function']['arguments'] }}{% else %}{{ tool_call['function']['arguments'] | tojson }}{% endif %}<|tool_call_end|>
+  {%- endfor -%}
+  <|tool_calls_section_end|>
+{%- endmacro -%}
+
+
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+{# Find last non-tool-call assistant message. If preserve_thinking, keep -1 so hist is empty and all msgs use suffix (retain reasoning). #}
+{%- set ns = namespace(last_non_tool_call_assistant_msg=-1) -%}
+{%- if not preserve_thinking -%}
+{%- for idx in range(messages|length-1, -1, -1) -%}
+    {%- if messages[idx]['role'] == 'assistant' and not messages[idx].get('tool_calls') -%}
+        {%- set ns.last_non_tool_call_assistant_msg = idx -%}
+        {%- break -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- endif -%}
+
+{# split all messages into history & suffix, reasoning_content in suffix should be reserved.#}
+{%- set hist_msgs = messages[:ns.last_non_tool_call_assistant_msg+1] -%}
+{%- set suffix_msgs = messages[ns.last_non_tool_call_assistant_msg+1:] -%}
+
+{%- if tools -%}
+  {%- if tools_ts_str -%}
+    <|im_system|>tool_declare<|im_middle|>{{ tools_ts_str }}<|im_end|>
+  {%- else -%}
+    <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
+  {%- endif -%}
+{%- endif -%}
+
+  
+{%- for message in hist_msgs -%}
+  {{set_roles(message)}}
+  {%- if message['role'] == 'assistant' -%}
+    <think></think>{{render_content(message)}}
+    {%- if message.get('tool_calls') -%}
+      {{render_toolcalls(message)}}
+    {%- endif -%}
+  {%- elif message['role'] == 'tool' -%}
+    {%- set tool_call_id = message.tool_call_id -%}
+    ## Return of {{ tool_call_id }}
+{{render_content(message)}}
+  {%- elif message['content'] is not none -%}
+    {{render_content(message)}}
+  {%- endif -%}
+  <|im_end|>
+{%- endfor -%}
+
+{%- for message in suffix_msgs -%}
+  {{set_roles(message)}}
+  {%- if message['role'] == 'assistant' -%}
+    {%- if thinking is defined and thinking is false and preserve_thinking is false -%}
+    <think></think>{{render_content(message)}}
+    {%- else -%}
+    {%- set rc = message.get('reasoning', message.get('reasoning_content', '')) -%}
+    <think>{{rc}}</think>{{render_content(message)}}
+    {%- endif -%}
+    {%- if message.get('tool_calls') -%}
+     {{render_toolcalls(message)}}
+    {%- endif -%}
+  {%- elif message['role'] == 'tool' -%}
+    {%- set tool_call_id = message.tool_call_id -%}
+    ## Return of {{ tool_call_id }}
+{{render_content(message)}}
+  {%- elif message['content'] is not none -%}
+    {{render_content(message)}}
+  {%- endif -%}
+  <|im_end|>
+{%- endfor -%}
+
+
+{%- if add_generation_prompt -%}
+  <|im_assistant|>assistant<|im_middle|>
+  {%- if thinking is defined and thinking is false -%}
+  <think></think>
+  {%- else -%}
+  <think>
+  {%- endif -%}
+{%- endif -%}

config.json

@@ -0,0 +1,55 @@
+{
+  "architectures": [
+    "DeepseekV3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "aux_loss_alpha": 0.001,
+  "bos_token_id": 163584,
+  "dtype": "bfloat16",
+  "eos_token_id": 163585,
+  "ep_size": 1,
+  "first_k_dense_replace": 1,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11264,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 131072,
+  "model_type": "deepseek_v3",
+  "moe_intermediate_size": 1408,
+  "moe_layer_freq": 1,
+  "n_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 2,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 27,
+  "num_key_value_heads": 16,
+  "num_nextn_predict_layers": 1,
+  "num_shared_experts": 2,
+  "pad_token_id": 163839,
+  "pretraining_tp": 1,
+  "q_lora_rank": null,
+  "qk_head_dim": 192,
+  "qk_nope_head_dim": 128,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_interleave": true,
+  "rope_parameters": {
+    "rope_theta": 800000.0,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 2.446,
+  "scoring_func": "sigmoid",
+  "seq_aux": true,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.8.1",
+  "use_cache": false,
+  "v_head_dim": 128,
+  "vocab_size": 163840
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 163584,
+  "eos_token_id": 163585,
+  "pad_token_id": 163839,
+  "transformers_version": "5.8.1"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274d30ab560204f3d6541d8659ada67d035c92e7cffc35c3363c24cb8ca7e271
+size 4996317112

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c46cbcfa3746f258bc1b6864a92fce7db31e769f52ca4f378bf169e3c934e347
+size 4699860696

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c59f09c53969cd299b304ae7abecd01fe3e29d7329915c9402a9a8e9ef65af8
+size 4678885128

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8bb4689c2a5a3268040c2286e99638ff87f032599f68532b9c39c342e8058f6
+size 4678885544

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84eab70972ac0607df07a52fcf580e1cd7c4cdd8847fd5a90f9115a59cd8306b
+size 4678885544

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401b78fe28c9772ef93ac4299c3a92941e0b4480f510d0263950529d91799d7b
+size 4678885544

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097ab416626579c57c09d731d5ea87713b54883e1887a1e178a1658b51582bbe
+size 3509164048

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261590fd5234433c558e867ea7d9b8d8a29ebc6bf51d9d43a9d714e4793db0e9
+size 19545255

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}