Update tiny models for Exaone4ForTokenClassification

chat_template.jinja

@@ -0,0 +1,146 @@
+{%- if not skip_think is defined %}
+  {%- set skip_think = true %}
+{%- endif %}
+
+{%- set role_indicators = {
+    'user': '[|user|]\n',
+    'assistant': '[|assistant|]\n',
+    'system': '[|system|]\n',
+    'tool': '[|tool|]\n'
+} %}
+{%- set end_of_turn = '[|endofturn|]\n' %}
+
+
+{%- macro available_tools(tools) %}
+    {{- "# Available Tools" }}
+    {{- "\nYou can use none, one, or multiple of the following tools by calling them as functions to help with the user’s query." }}
+    {{- "\nHere are the tools available to you in JSON format within <tool> and </tool> tags:\n" }}
+    {%- for tool in tools %}
+        {{- "<tool>" }}
+        {{- tool | tojson(ensure_ascii=False) | safe }}
+        {{- "</tool>\n" }}
+    {%- endfor %}
+
+    {{- "\nFor each function call you want to make, return a JSON object with function name and arguments within <tool_call> and </tool_call> tags, like:" }}
+    {{- "\n<tool_call>{\"name\": function_1_name, \"arguments\": {argument_1_name: argument_1_value, argument_2_name: argument_2_value}}</tool_call>" }}
+    {{- "\n<tool_call>{\"name\": function_2_name, \"arguments\": {...}}</tool_call>\n..." }}
+    {{- "\nNote that if no argument name is specified for a tool, you can just print the argument value directly, without the argument name or JSON formatting." }}
+{%- endmacro %}
+
+
+{%- set ns = namespace(last_query_index = messages|length - 1) %}
+{%- for message in messages %}
+    {%- if message.role == "user" and message.content is string %}
+        {%- set ns.last_query_index = loop.index0 -%}
+    {%- endif %}
+{%- endfor %}
+
+{%- for i in range(messages | length) %}
+    {%- set msg = messages[i] %}
+    {%- set role = msg.role %}
+    {%- if role not in role_indicators %}
+        {{- raise_exception('Unknown role: ' ~ role) }}
+    {%- endif %}
+    
+    {%- if i == 0 %}
+        {%- if role == 'system' %}
+            {{- role_indicators['system'] }}
+            {{- msg.content }}
+            {%- if tools is defined and tools %}
+                {{- "\n\n" }}{{- available_tools(tools) }}
+            {%- endif %}
+            {{- end_of_turn -}}
+            {%- continue %}
+        {%- elif tools is defined and tools %}            
+            {{- role_indicators['system'] }}
+            {{- available_tools(tools) }}
+            {{- end_of_turn -}}            
+        {%- endif %}
+    {%- endif %}
+
+    {%- if role == 'assistant' %}
+        {{- role_indicators['assistant'] }}
+
+        {%- if msg.content %}        
+            {%- if "</think>" in msg.content %}
+                {%- set content = msg.content.split('</think>')[-1].strip() %}
+                {%- set reasoning_content = msg.content.split('</think>')[0].strip() %}
+                {%- if reasoning_content.startswith("<think>") %}
+                    {%- set reasoning_content = reasoning_content[9:].strip() %}
+                {%- endif %}
+            {%- else %}
+                {%- set content = msg.content %}
+            {%- endif %}
+
+            {%- if msg.reasoning_content %}
+                {%- set reasoning_content = msg.reasoning_content %}
+            {%- endif %}
+
+            {%- if (not skip_think and loop.last) and reasoning_content is defined %}
+                {{- "<think>\n" }}
+                {{- reasoning_content}}
+                {{- "\n</think>\n\n" }}
+            {%- else %}
+                {{- "<think>\n\n</think>\n\n" }}
+            {%- endif %}
+            {{- content }}
+        {%- endif %}
+
+        {%- if msg.tool_calls %}
+            {%- if msg.content %}
+                {{- "\n" }}
+            {%- else %}
+                {{- "<think>\n\n</think>\n\n" }}
+            {%- endif %}
+            {%- for tool_call in msg.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+
+                {%- if tool_call.arguments is defined %}
+                    {%- set arguments = tool_call.arguments %}
+                {%- elif tool_call.parameters is defined %}
+                    {%- set arguments = tool_call.parameters %}
+                {%- else %}
+                    {{- raise_exception('arguments or parameters are mandatory: ' ~ tool_call) }}
+                {%- endif %}
+
+                {{- "<tool_call>" }}{"name": "{{- tool_call.name }}", "arguments": {{ arguments | tojson(ensure_ascii=False) | safe }}}{{- "</tool_call>" }}
+
+                {%- if not loop.last %}
+                    {{- "\n" }}
+                {%- endif %}
+
+            {%- endfor %}
+        {%- endif %}
+        {{- end_of_turn -}}
+
+    {%- elif role == "tool" %}
+        {%- if i == 0 or messages[i - 1].role != "tool" %}
+            {{- role_indicators['tool'] }}
+        {%- endif %}
+        {%- if msg.content is defined %}            
+            {{- "<tool_result>" }}{"result": {{ msg.content | tojson(ensure_ascii=False) | safe }}}{{- "</tool_result>" }}            
+        {%- endif %}
+        {%- if loop.last or messages[i + 1].role != "tool" %}
+            {{- end_of_turn -}}
+        {%- else %}
+            {{- "\n" }}
+        {%- endif %}
+
+    {%- else %}
+        {{- role_indicators[role] }}
+        {{- msg.content }}
+        {{- end_of_turn -}}
+    {%- endif %}
+{% endfor %}
+
+
+{%- if add_generation_prompt %}
+    {{- role_indicators['assistant'] }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- "<think>\n" }}
+    {%- else %}
+        {{- "<think>\n\n</think>\n\n" }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "Exaone4ForTokenClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 361,
+  "hidden_act": "gelu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 512,
+  "model_type": "exaone4",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": 4096,
+  "sliding_window_pattern": 4,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 102400
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a5535430cad4ce4417ff4aaf599370a22183c6920c19b79398a23444363932
+size 13168448

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[|endofturn|]",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "[UNK]"
+}