Upload merged EXAONE 1.2B Float:Right tagger (merged weights + tokenizer + template)

README.md

@@ -0,0 +1,79 @@
+---
+license: other
+base_model: LGAI-EXAONE/EXAONE-4.0-1.2B
+tags:
+  - exaone
+  - lora
+  - finetune
+  - korean
+  - tagger
+  - text-classification
+  - text-generation
+library_name: transformers
+---
+
+# EXAONE-4.0-1.2B Tagger (Merged)
+
+This repository contains a **merged** checkpoint of:
+- **Base**: `LGAI-EXAONE/EXAONE-4.0-1.2B`
+- **LoRA fine-tune**: a lightweight SFT adapter trained to behave as a **Korean tag generator**.
+
+The model is designed to output **a JSON array of 3–10 high-level tags** for a given Korean sentence.
+
+## Intended Behavior
+
+Given an input sentence, the model should output **ONLY** a JSON array:
+- 3–10 tags
+- high-level topics (not overly detailed)
+- no underscores `_`
+- **no extra text** (ideally)
+
+In practice, some runs may emit extra text (e.g., reasoning markers).  
+For production, parse the first JSON array from the output.
+
+## Quick Start (Transformers)
+
+```python
+import re, json, torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+MODEL = "<this_repo_or_local_path>"
+
+def extract_first_json_array(s: str):
+    m = re.search(r"$begin:math:display$\[\\s\\S\]\*\?$end:math:display$", s)
+    return json.loads(m.group(0)) if m else None
+
+tok = AutoTokenizer.from_pretrained(MODEL, trust_remote_code=True, use_fast=True)
+if tok.pad_token is None:
+    tok.pad_token = tok.eos_token
+
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL, trust_remote_code=True, torch_dtype="auto", device_map="cuda"
+).eval()
+
+messages = [
+  {"role":"system","content":"너는 태그 생성기다. 반드시 JSON 배열만 출력한다. 다른 글자 금지."},
+  {"role":"user","content":"규칙: 태그 3~10개, 큰 주제, 언더스코어 금지, JSON 배열만. 문장: 직장 상사가 계속 야근을 시켜서 스트레스 받는다. 퇴사 고민 중."}
+]
+
+prompt = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+enc = tok(prompt, return_tensors="pt").to("cuda")
+
+out = model.generate(**enc, max_new_tokens=64, do_sample=False, temperature=0.0,
+                     pad_token_id=tok.pad_token_id, eos_token_id=tok.eos_token_id)
+
+text = tok.decode(out[0], skip_special_tokens=True)
+tags = extract_first_json_array(text)
+print("RAW:", text)
+print("TAGS:", tags)
+
+
+Training Notes
+	•	This is not a general chat model tuning.
+	•	The objective is to improve consistency of tag-only outputs for Korean input.
+	•	If you need strict JSON-only output, use a post-processor that extracts the first JSON array.
+
+Quantization / GGUF
+
+A GGUF / quantized release may be provided separately.
+

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 +1,67 @@
+{
+  "architectures": [
+    "Exaone4ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 361,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 65536,
+  "model_type": "exaone4",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 16.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 1000000.0,
+    "rope_type": "llama3"
+  },
+  "sliding_window": null,
+  "sliding_window_pattern": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": true,
+  "vocab_size": 102400
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 361,
+  "pad_token_id": 0,
+  "transformers_version": "5.2.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87288afa2a34830a2fceed835549c64f7036e64e60d504e110d1b058c8a8c7a3
+size 2558820960

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "[|endofturn|]",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "[UNK]"
+}