Update tiny models for HyperCLOVAXForCausalLM

chat_template.jinja

@@ -0,0 +1,108 @@
+{% if tools is not defined or tools is none %}
+    {{- '<|im_start|>tool_list\n<|im_end|>\n' }}
+{%- else %}
+    {{- '<|im_start|>tool_list\n[' }}
+    {%- for tool in tools %}
+        {{- '{"name": "' }}
+        {{- tool.function.name }}
+        {{- '", ' }}
+        {{- '"description": "' }}
+        {{- tool.function.description }}
+        {{- '"' }}
+        {%- if tool.function.parameters is defined %}
+            {{- ', "parameters": ' }}
+            {{- tool.function.parameters | tojson }}
+        {%- endif %}
+        {{- '}' }}
+        {%- if not loop.last %}
+            {{- ', ' }}
+        {%- endif %}
+    {%- endfor %}
+{{- ']<|im_end|>\n' }}
+{%- endif %}
+
+{%- set ns = namespace(is_searching=true, last_query_index=-1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.is_searching and (message.role == 'user' or message.role == 'tool') %}
+        {%- set ns.last_query_index = index %}
+        {%- set ns.is_searching = false %}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages %}
+    {%- if loop.index0 == 0 and message.role != 'system' %}
+        {{- '<|im_start|>system\n<|im_end|>\n' }}
+    {%- endif %}
+
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- elif message.content is iterable and message.content is not none %}
+        {%- set ns_content = namespace(text='') %}
+        {%- for part in message.content %}
+            {%- if part.type is defined and part.type == 'text' and part.text is defined %}
+                {%- set ns_content.text = ns_content.text + part.text %}
+            {%- endif %}
+        {%- endfor %}
+        {%- set content = ns_content.text %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+
+    {%- set reasoning_content = '' %}
+    {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+        {%- set reasoning_content = message.reasoning_content %}    
+    {%- endif %}
+    {%- if message.role == "assistant" %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if reasoning_content %}
+                {{- '<|im_start|>assistant/think\n' + reasoning_content.strip('\n') + '<|im_end|>\n' }}
+            {%- endif %}
+        {%- endif %}
+
+        {%- if content %}
+            {{- '<|im_start|>assistant\n' + content.strip('\n') + '<|im_end|>' }}
+            {%- if message.tool_calls %}
+                {{- '\n' }}
+            {%- else %}
+                {{- '<|endofturn|>\n' }}
+            {%- endif %}
+        {%- endif %}
+
+        {%- if message.tool_calls %}
+            {{- '<|im_start|>assistant -> tool/function_call\n[' }}
+            {%- for tool_call in message.tool_calls %}
+                {%- if not loop.first %}
+                    {{- ', ' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}' }}
+                {%- endfor %}
+            {{- ']<|im_end|><|stop|>\n' }}
+
+        {%- endif %}
+    {%- elif message.role == "tool" %}
+        {{- '<|im_start|>tool/function_call\n' + content + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {%- if force_reasoning is defined and force_reasoning is true %}
+        {{- '<|im_start|>assistant/think\n' }}
+    {%- elif skip_reasoning is defined and skip_reasoning is true %}
+        {{- '<|im_start|>assistant/think\n<|im_end|>\n<|im_start|>assistant\n' }}
+    {%- else %}
+        {{- '<|im_start|>assistant' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "HyperCLOVAXForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 0.25,
+  "bos_token_id": 100257,
+  "dtype": "float32",
+  "embedding_multiplier": 1.0,
+  "eos_token_id": 100257,
+  "head_dim": 16,
+  "hidden_act": "gelu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "is_decoder": true,
+  "logits_scaling": 1.0,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "hyperclovax",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 100257,
+  "residual_multiplier": 1.0,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "use_post_norm": true,
+  "vocab_size": 110524
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 100257,
+  "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:b6589673ac6270e12c04ae6da3f5f9c99f19fb9f07b594851941215c91337af6
+size 28355264

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>"
+}