Fine-tuning is based on the foundation model version v2024.12.28, and it uses self-prepared instruction datasets for this round of fine-tuning.

README.md

@@ -24,12 +24,9 @@ datasets:
 - lianghsun/tw-contract-review-chat
 - lianghsun/reasoning-base-20k-chat
 - lianghsun/vulnerability-mitigation-qa-zh_tw
-- benchang1110/Belle-Taide
+- lianghsun/tw-instruct
 - rombodawg/Everything_Instruct_Multilingual
-- BAAI/Infinity-Instruct
-- nisaar/LLAMA2_Legal_Dataset_4.4k_Instructions
 - xzuyn/manythings-translations-alpaca
-- neural-bridge/rag-hallucination-dataset-1000
 - neural-bridge/rag-dataset-12000
 - minyichen/glaive_toolcall_zh_tw
 pipeline_tag: text-generation
@@ -999,6 +996,7 @@ metrics:
   
   | Update Date  | Model Version         | Key Changes                         |
   |--------------|-----------------------|-------------------------------------|
+  | 2025/01/01   | v2025.01.01           | Fine-tuning is based on the [foundation model](https://huggingface.co/lianghsun/Llama-3.2-Taiwan-3B) version v2024.12.28, and it uses self-prepared instruction datasets for this round of fine-tuning. |
   | 2024/11/27   | v2024.11.27           | Completed SFT training (5/5 epochs). Preparing for multi-round DPO training. |
   | 2024/11/25   | v2024.11.25           | Updated model version to v2024.11.25, training progressed to (3/5) epochs. Still in SFT stage, DPO training remains pending. |
   | 2024/11/22   | v2024.11.22           | Initial upload: Model version v2024.11.22, training completed up to (1/5) epochs. Currently trained only on SFT, DPO training not yet performed. |
@@ -1096,7 +1094,6 @@ docker run --runtime nvidia --gpus all \
   - [lianghsun/tw-law-article-qa](https://huggingface.co/datasets/lianghsun/tw-law-article-qa)
   - [lianghsun/tw-judgment-qa](https://huggingface.co/datasets/lianghsun/tw-judgment-qa)
   - [lianghsun/tw-bar-examination-2020-chat](https://huggingface.co/datasets/lianghsun/tw-bar-examination-2020-chat)
-  - [lianghsun/tw-emergency-medicine-bench](https://huggingface.co/datasets/lianghsun/tw-emergency-medicine-bench)
   - [lianghsun/tw-structured-law-article](https://huggingface.co/datasets/lianghsun/tw-structured-law-article)
   - [lianghsun/tw-judgment-gist-chat](https://huggingface.co/datasets/lianghsun/tw-judgment-gist-chat)
   - [lianghsun/vulnerability-mitigation-qa-zh_tw](https://huggingface.co/datasets/lianghsun/vulnerability-mitigation-qa-zh_tw)
@@ -1104,7 +1101,6 @@ docker run --runtime nvidia --gpus all \
   - [lianghsun/reasoning-base-20k-chat](https://huggingface.co/datasets/lianghsun/reasoning-base-20k-chat)
   - [lianghsun/tw-contract-review-chat](https://huggingface.co/datasets/lianghsun/tw-contract-review-chat)
   - [lianghsun/tw-legal-methodology-chat](https://huggingface.co/datasets/lianghsun/tw-legal-methodology-chat)
-  - [benchang1110/Belle-Taide](https://huggingface.co/datasets/benchang1110/Belle-Taide)
   - [minyichen/glaive_toolcall_zh_tw](https://huggingface.co/datasets/minyichen/glaive_toolcall_zh_tw)
   
 </details>
@@ -1113,11 +1109,8 @@ docker run --runtime nvidia --gpus all \
   <summary><b>多國語系對話資料集</b></summary>
   
   - [rombodawg/Everything_Instruct_Multilingual](https://huggingface.co/datasets/rombodawg/Everything_Instruct_Multilingual)
-  - [BAAI/Infinity-Instruct](https://huggingface.co/datasets/BAAI/Infinity-Instruct)
-  - [nisaar/LLAMA2_Legal_Dataset_4.4k_Instructions](https://huggingface.co/datasets/nisaar/LLAMA2_Legal_Dataset_4.4k_Instructions)
   - [xzuyn/manythings-translations-alpaca](https://huggingface.co/datasets/xzuyn/manythings-translations-alpaca)
   - [neural-bridge/rag-dataset-12000](https://huggingface.co/datasets/neural-bridge/rag-dataset-12000)
-  - [neural-bridge/rag-hallucination-dataset-1000](https://huggingface.co/datasets/neural-bridge/rag-hallucination-dataset-1000)
 
 </details>
 
@@ -1125,10 +1118,9 @@ docker run --runtime nvidia --gpus all \
 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
-#### Preprocessing [optional]
-
-[More Information Needed]
+#### Preprocessing
 
+(WIP)
 
 #### Training Hyperparameters
 
@@ -1416,4 +1408,4 @@ base_model: lianghsun/Llama-3.2-Taiwan-3B-Instruct
 - Transformers 4.45.2
 - Pytorch 2.4.1+cu121
 - Datasets 2.21.0
-- Tokenizers 0.20.0
+- Tokenizers 0.20.0

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2bff44179e46840bdba4d0101f5160ab7f3302625ec4e75f5a186868de2d6ee
+oid sha256:c114557d56bfbec77c9c763cc71c1a04c1668566636cfe4d1d489f3ddb9f4ff7
 size 4965799096

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:203ed4c8f522e3d6b4f08b6931d8db0c9a3aae352bdb6e19f20ad22a78a57593
-size 1459729952
+oid sha256:6e20fae2caad0bd2dadabd50a7e5524a4421ecfe29b4b3b0aad1c1d0fab9de16
+size 2247734992