SN97 gauged model commit

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-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c94f240a431f2cd788b598b62f270e2b36fb3ee2b90831140298b30f3cb124
+size 3847571800

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:851c1412709e9022a3a4b4546b2d0d03a1c0d10489369a56d1e0945397fce5de
+size 3878270200

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f098553aec3faea3fd209dddfbaf64efca4257780c84b2daebef4623bd00d80
+size 3509163456

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76860fcbdc1759353827ab018c3bbca94ecf07b5e668c6fc2f7bd18c72478c32
+size 3509163920

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a670c03660fc6c58a6fb4ee6989ab229543e8b76d77c262b3e21e587610296
+size 3509164072

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c727c4e190342eb52f2ea3397cbeccabac523725eb4bb73e0165f06194d9d5c
+size 3509164072

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30385b77efa379b2329a376d0797ae42f9719b83268ba39d3983d49e88ef5b9e
+size 3509164072

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36855a2536c16793f42a8e9e12ba6831ed2041db8004be326881b8512d4ea9ce
+size 3509164072

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e42e29bc951e0d86832a38e061c908d36bb2a8b5904b35d22eef31a6959c6f
+size 3140057248

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "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]",
+  "chat_template": "{%- macro render_content(msg) -%}\n    {%- set c = msg.get('content') -%}\n    {%- if c is string -%}\n      {{ c }}\n    {%- elif c is not none -%}\n      {% for content in c -%}\n        {% if content['type'] == 'image' or content['type'] == 'image_url' -%}\n          <|media_begin|>image<|media_content|><|media_pad|><|media_end|>\n        {% elif content['type'] == 'video' or content['type']== 'video_url'-%}\n          <|kimi_k25_video_placeholder|>\n        {% else -%}\n          {{ content['text'] }}\n        {%- endif -%}\n      {%- endfor -%}\n    {%- endif -%}\n{%- endmacro -%}\n\n{% macro set_roles(message) -%}\n  {%- set role_name =  message.get('name') or  message['role'] -%}\n  {%- if message['role'] == 'user' -%}\n    <|im_user|>{{role_name}}<|im_middle|>\n  {%- elif message['role'] == 'assistant' -%}\n    <|im_assistant|>{{role_name}}<|im_middle|>\n  {%- else -%}\n    <|im_system|>{{role_name}}<|im_middle|>\n  {%- endif -%}\n{%- endmacro -%}\n\n\n{%- macro render_toolcalls(message) -%}\n  <|tool_calls_section_begin|>\n  {%- for tool_call in message['tool_calls'] -%}\n    {%- set formatted_id = tool_call['id'] -%}\n    <|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|>\n  {%- endfor -%}\n  <|tool_calls_section_end|>\n{%- endmacro -%}\n\n\n{%- set preserve_thinking = preserve_thinking | default(false) -%}\n{# Find last non-tool-call assistant message. If preserve_thinking, keep -1 so hist is empty and all msgs use suffix (retain reasoning). #}\n{%- set ns = namespace(last_non_tool_call_assistant_msg=-1) -%}\n{%- if not preserve_thinking -%}\n{%- for idx in range(messages|length-1, -1, -1) -%}\n    {%- if messages[idx]['role'] == 'assistant' and not messages[idx].get('tool_calls') -%}\n        {%- set ns.last_non_tool_call_assistant_msg = idx -%}\n        {%- break -%}\n    {%- endif -%}\n{%- endfor -%}\n{%- endif -%}\n\n{# split all messages into history & suffix, reasoning_content in suffix should be reserved.#}\n{%- set hist_msgs = messages[:ns.last_non_tool_call_assistant_msg+1] -%}\n{%- set suffix_msgs = messages[ns.last_non_tool_call_assistant_msg+1:] -%}\n\n{%- if tools -%}\n  {%- if tools_ts_str -%}\n    <|im_system|>tool_declare<|im_middle|>{{ tools_ts_str }}<|im_end|>\n  {%- else -%}\n    <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>\n  {%- endif -%}\n{%- endif -%}\n\n  \n{%- for message in hist_msgs -%}\n  {{set_roles(message)}}\n  {%- if message['role'] == 'assistant' -%}\n    <think></think>{{render_content(message)}}\n    {%- if message.get('tool_calls') -%}\n      {{render_toolcalls(message)}}\n    {%- endif -%}\n  {%- elif message['role'] == 'tool' -%}\n    {%- set tool_call_id = message.tool_call_id -%}\n    ## Return of {{ tool_call_id }}\n{{render_content(message)}}\n  {%- elif message['content'] is not none -%}\n    {{render_content(message)}}\n  {%- endif -%}\n  <|im_end|>\n{%- endfor -%}\n\n{%- for message in suffix_msgs -%}\n  {{set_roles(message)}}\n  {%- if message['role'] == 'assistant' -%}\n    {%- if thinking is defined and thinking is false and preserve_thinking is false -%}\n    <think></think>{{render_content(message)}}\n    {%- else -%}\n    {%- set rc = message.get('reasoning', message.get('reasoning_content', '')) -%}\n    <think>{{rc}}</think>{{render_content(message)}}\n    {%- endif -%}\n    {%- if message.get('tool_calls') -%}\n     {{render_toolcalls(message)}}\n    {%- endif -%}\n  {%- elif message['role'] == 'tool' -%}\n    {%- set tool_call_id = message.tool_call_id -%}\n    ## Return of {{ tool_call_id }}\n{{render_content(message)}}\n  {%- elif message['content'] is not none -%}\n    {{render_content(message)}}\n  {%- endif -%}\n  <|im_end|>\n{%- endfor -%}\n\n\n{%- if add_generation_prompt -%}\n  <|im_assistant|>assistant<|im_middle|>\n  {%- if thinking is defined and thinking is false -%}\n  <think></think>\n  {%- else -%}\n  <think>\n  {%- endif -%}\n{%- endif -%}"
+}