Upload 6 files

.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 +1,48 @@
+{% 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 'image' in content or 'image_url' in content -%}
+          <|media_start|>image<|media_content|><|media_pad|><|media_end|>
+        {% else -%}
+          {{ content['text'] }}
+        {%- endif -%}
+      {%- endfor -%}
+    {%- endif -%}
+{%- endmacro %}
+
+
+{%- if tools -%}
+  <|im_system|>tool_declare<|im_middle|>{{ tools | tojson(separators=(',', ':')) }}<|im_end|>
+{%- endif -%}
+{% for message in messages %}  
+  {%- 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 -%}
+
+  {%- if message['role'] == 'assistant' and message.get('tool_calls') -%}
+    {{render_content(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|>
+  {%- 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|>
+{%- endif -%}

config.json

@@ -0,0 +1,56 @@
+{
+  "architectures": [
+    "KimiLinearForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 163584,
+  "dtype": "bfloat16",
+  "eos_token_id": 163586,
+  "head_dim": 8,
+  "hidden_act": "silu",
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 128,
+  "kv_lora_rank": 16,
+  "layer_types": [
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention"
+  ],
+  "linear_conv_kernel_dim": 4,
+  "linear_head_dim": 16,
+  "linear_num_heads": 4,
+  "max_position_embeddings": 1024,
+  "mlp_layer_types": [
+    "dense",
+    "sparse",
+    "sparse",
+    "sparse"
+  ],
+  "model_type": "kimi_linear",
+  "moe_intermediate_size": 32,
+  "n_group": 1,
+  "n_routed_experts": 8,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 4,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 4,
+  "pad_token_id": 163839,
+  "pretraining_tp": 1,
+  "q_lora_rank": null,
+  "qk_head_dim": 24,
+  "qk_nope_head_dim": 16,
+  "qk_rope_head_dim": 8,
+  "rms_norm_eps": 1e-05,
+  "routed_scaling_factor": 2.446,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "v_head_dim": 16,
+  "vocab_size": 163840
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 163584,
+  "eos_token_id": 163586,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 163839,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a05f47fabe2b2785a6923507b15f0a49445ab488db609b14f3941411ed8db1
+size 42503160

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96894d7eb8bd9ce759df54963eb77bdbcf709e329a8007ed5f5cb402b9b1615b
+size 19592396

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_kimi.TikTokenTokenizer",
+      null
+    ]
+  },
+  "backend": "tokenizers",
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[EOS]",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}