初始化项目，由ModelHub XC社区提供模型

Model: sh-024/LFM2.5-1.2B-Instruct-Korean
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,117 @@
+
+---
+datasets:
+- maywell/koVast
+- CarrotAI/ko-instruction-dataset
+- MarkrAI/KoCommercial-Dataset
+base_model:
+- LiquidAI/LFM2.5-1.2B-Instruct
+language:
+- ko
+pipeline_tag: text-generation
+library_name: transformers
+license: other
+license_name: lfm-open-license-v1.0
+license_link: https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct/blob/main/LICENSE
+tags:
+- unsloth
+- lfm2
+- lfm2.5
+- korean
+- text-generation
+- conversational
+- instruction-tuned
+---
+# LFM2.5-1.2B-Instruct-Korean
+
+## Model Overview
+
+`LFM2.5-1.2B-Instruct-Korean` is a Korean instruction-following language model based on `LiquidAI/LFM2.5-1.2B-Instruct`.  
+This model was fine-tuned on Korean-centered datasets with the goal of improving performance on Korean question answering, general conversation, and instruction-following tasks.
+
+The model is designed to generate responses that are more natural, consistent, and contextually appropriate in Korean.
+
+## Base Model
+
+- **Base model**: `LiquidAI/LFM2.5-1.2B-Instruct`
+
+## Training Data
+
+This model was fine-tuned using the following Korean-centered datasets:
+
+- `maywell/koVast`
+- `CarrotAI/ko-instruction-dataset`
+- `MarkrAI/KoCommercial-Dataset`
+
+The training data includes Korean instruction-response pairs, general conversational data, and commercially or practically oriented text.  
+This setup was intended to help the model learn a broad range of Korean expressions, styles, and contexts.
+
+## Training Details
+
+The model was trained for **1 full epoch** over the entire dataset.  
+Training proceeded for a total of **25,652 steps** and was completed successfully without interruption.
+
+### Training Summary
+
+- **Number of epochs**: 1
+- **Total training steps**: 25,652
+- **Training completion status**: Completed
+- **Training status**: Stable
+
+## Evaluation Results
+
+The final evaluation metrics are as follows:
+
+- **training_loss**: 1.1046
+- **eval_loss**: 1.1015
+- **eval_perplexity**: 3.0087
+
+These results show that the training loss and evaluation loss remained at nearly the same level, suggesting that the model demonstrated relatively stable generalization performance on the validation set without a clear sign of overfitting.
+
+## Result Interpretation
+
+One notable point in this experiment is the very small gap between **training loss** and **evaluation loss**.
+
+- **training_loss = 1.1046**
+- **eval_loss = 1.1015**
+
+In general, a large gap between these two values may indicate overfitting.  
+However, in this experiment, the difference was very small, which suggests that the model adapted to the training data in a stable manner while maintaining a similar level of performance on the validation set.
+
+In addition, the result of **eval_perplexity = 3.0087** indicates that the model predicts the next token in a relatively stable and consistent way.  
+Taken together, these results suggest that the model successfully learned the major patterns in the training data and converged stably without severe instability.
+
+## Overall Conclusion
+
+This fine-tuning was completed successfully and showed overall solid results.  
+The close alignment between training loss and evaluation loss suggests that the model did not significantly overfit during training and that the optimization process remained stable.
+
+Moreover, no sharp divergence in loss values was observed throughout the training process.  
+Therefore, this experiment can be regarded as a fine-tuning run that converged stably overall.
+
+## Limitations and Future Work
+
+While these metrics are useful for assessing training stability and convergence, they do not fully reflect response quality, factuality, instruction-following accuracy, or real-world usability.
+
+To obtain a more comprehensive evaluation of the model, the following additional assessments are planned:
+
+- evaluation on real user question-answer examples
+- downstream task performance evaluation
+- qualitative analysis of generated responses
+- safety and hallucination checks
+
+Through these follow-up evaluations, we aim to verify whether the model can go beyond stable training-time metrics and provide reliable and consistent performance in real-world usage scenarios.
+
+## License
+
+This model is a fine-tuned derivative of `LiquidAI/LFM2.5-1.2B-Instruct`.
+
+Use and distribution of this model are subject to the terms of the **LFM Open License v1.0** applicable to the base model.
+
+Please also review any additional obligations arising from the datasets used during fine-tuning.
+
+## Feedback
+
+This model will continue to be improved through further evaluation and refinement.  
+If you have any feedback on your experience using the model or notice areas that need improvement, your input will be carefully considered and reflected in future quality improvements.  
+Your feedback will be a great source of support in improving and further developing the model.

chat_template.jinja

@@ -0,0 +1,45 @@
+{{- bos_token -}}
+{%- set keep_past_thinking = keep_past_thinking | default(false) -%}
+{%- set ns = namespace(system_prompt="") -%}
+{%- if messages[0]["role"] == "system" -%}
+    {%- set ns.system_prompt = messages[0]["content"] -%}
+    {%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+    {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
+    {%- for tool in tools -%}
+        {%- if tool is not string -%}
+            {%- set tool = tool | tojson -%}
+        {%- endif -%}
+        {%- set ns.system_prompt = ns.system_prompt + tool -%}
+        {%- if not loop.last -%}
+            {%- set ns.system_prompt = ns.system_prompt + ", " -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns.system_prompt = ns.system_prompt + "]" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+    {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- set ns.last_assistant_index = -1 -%}
+{%- for message in messages -%}
+    {%- if message["role"] == "assistant" -%}
+        {%- set ns.last_assistant_index = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- for message in messages -%}
+    {{- "<|im_start|>" + message["role"] + "\n" -}}
+    {%- set content = message["content"] -%}
+    {%- if content is not string -%}
+        {%- set content = content | tojson -%}
+    {%- endif -%}
+    {%- if message["role"] == "assistant" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
+        {%- if "</think>" in content -%}
+            {%- set content = content.split("</think>")[-1] | trim -%}
+        {%- endif -%}
+    {%- endif -%}
+    {{- content + "<|im_end|>\n" -}}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "<|im_start|>assistant\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block_auto_adjust_ff_dim": true,
+  "block_dim": 2048,
+  "block_ff_dim": 12288,
+  "block_ffn_dim_multiplier": 1.0,
+  "block_mlp_init_scale": 1.0,
+  "block_multiple_of": 256,
+  "block_norm_eps": 1e-05,
+  "block_out_init_scale": 1.0,
+  "block_use_swiglu": true,
+  "block_use_xavier_init": true,
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "conv_dim": 2048,
+  "conv_use_xavier_init": true,
+  "dtype": "bfloat16",
+  "eos_token_id": 7,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv"
+  ],
+  "max_position_embeddings": 128000,
+  "model_type": "lfm2",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 32,
+  "num_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "tie_embedding": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": true,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}

generation_config.json

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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de6f09639237db0bea037a42404792356cb91ca5695c4557ec840e5f1ce971d
+size 2340697936

tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": true,
+  "legacy": false,
+  "max_length": 2000,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|pad|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null,
+  "use_default_system_prompt": false,
+  "use_fast": true
+}