upload model weights and model card

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,108 @@
 ---
 license: llama3.1
+datasets:
+- survivi/Llama-3-SynE-Dataset
+- hfl/stem_zh_instruction
+- llamafactory/alpaca_zh
+- llamafactory/alpaca_gpt4_zh
+- hfl/ruozhiba_gpt4
+- codingsteven/Llama-3-8B-chat
+language:
+- zh
+base_model:
+- meta-llama/Llama-3.1-8B-Instruct
+model-index:
+- name: Control-LLM-Llama3.1-8B-SynE-Full-Parameter-Tuning
+  results:
+  - task:
+      type: pretraining-evaluation
+    dataset:
+      type: mixed
+      name: Pretraining Evaluation Dataset
+    metrics:
+    - name: exact_match,strict-match (meta_pretrain)
+      type: exact_match
+      value: 0.45445720757159036
+      stderr: 0.0035036029889520047
+      verified: false
+    - name: exact_match,strict-match (meta_bbh_3shot_cot_pretrain)
+      type: exact_match
+      value: 0.6482875134387959
+      stderr: 0.005918167158231359
+      verified: false
+    - name: acc,none (meta_mmlu_5shot_pretrain)
+      type: accuracy
+      value: 0.649480131035465
+      stderr: 0.004026616190778244
+      verified: false
+    - name: exact_match,strict-match (meta_mmlu_pro_5shot_pretrain)
+      type: exact_match
+      value: 0.34956781914893614
+      stderr: 0.004347262544061378
+      verified: false
+  - task:
+      type: chinese-evaluation
+    dataset:
+      type: mixed
+      name: Chinese Evaluation Dataset
+    metrics:
+    - name: acc,none (ceval-valid)
+      type: accuracy
+      value: 0.5898959881129272
+      stderr: 0.012699457390113113
+      verified: false
+    - name: exact_match,strict-match (ceval-valid-pretrain-cot_zh)
+      type: exact_match
+      value: 0.40193164933135217
+      stderr: 0.01265090064840271
+      verified: false
+    - name: acc,none (cmmlu)
+      type: accuracy
+      value: 0.6018822310481782
+      stderr: 0.004420298073040671
+      verified: false
+    - name: exact_match,strict-match (cmmlu_pretrain_cot_zh)
+      type: exact_match
+      value: 0.4425833189431877
+      stderr: 0.004506238417180843
+      verified: false
+
 ---
+# Control-LLM-Llama3.1-8B-SynE-Full-Parameter-Tuning
+This is a fine-tuned model of Llama-3.1-8B for muliligual-Chinese tasks on SynE dataset.
+
+## Evaluation Results
+Here is an overview of the evaluation results and findings:
+
+### Benchmark Results Table
+
+The table below summarizes evaluation results across Chinese tasks and original capabilities.
+
+| **Model**          | **CEval** | **CEvalC** | **CMMLU** | **CMMLUC** | **C-Avg** | **BBH** | **MLU** | **MLUP** | **O-Avg** | **Overall** |
+|--------------------|-----------|------------|-----------|------------|-----------|---------|---------|----------|-----------|-------------|
+| Llama3.1-8B        | 48.3      | 12.8       | 51.1      | 14.1       | 13.9      | 65.2    | 65.4    | 35.5     | 45.9      | 29.9        |
+| Llama-3-SynE       | 57.7      | 22.3       | 57.1      | 22.8       | 22.8      | 61.9    | 64.0    | 32.6     | 42.9      | 32.9        |
+| **Full Param Tune**| 59.0      | 40.2       | **60.2**  | 44.3       | 43.8      | 64.8    | 64.9    | 35.0     | 45.4      | 44.6        |
+| Stack Expansion    | 56.0      | 32.7       | 55.2      | 33.4       | 33.3      | 62.3    | 65.6    | 35.3     | 44.8      | 39.1        |
+| Concat-Lerp*       | 57.1      | 34.8       | 57.0      | 37.4       | 37.1      | 64.4    | 64.6    | 35.8     | 45.9      | 41.5        |
+| **Hybrid Expansion**| **58.9** | 44.7       | 57.9      | 44.3       | 44.4      | 65.1    | **65.7**| 36.9     | 46.8      | 45.6        |
+| **Control LLM***   | 57.0      | **44.7**   | 56.0      | **44.9**   | **44.8**  | **68.2**| 65.6    | **37.9** | **48.5**  | **46.7**    |
+
+---
+
+### Explanation:
+- **CEval**: Chinese Evaluation
+- **CEvalC**: Chinese Evaluation (CoT - Chain of Thought)
+- **CMMLU**: Chinese MMLU
+- **CMMLUC**: Chinese MMLU (CoT)
+- **C-Avg**: Chinese - Size Weighted Average across CEval, CEvalC, CMMLU, and CMMLUC
+- **BBH**: BigBench Hard
+- **MLU**: MMLU (Massive Multitask Language Understanding)
+- **MLUP**: MMLU Pro
+- **O-Avg**: Original Capability - Size Weighted Average across BBH, MLU, and MLUP
+- **Overall**: Combined average across all tasks
+
+### Full Parameter Tuning on Chinese-SynE
+The following plot illustrates the Catastrophic Forgetting of full parameter tuning in terms of hidden states alignment drift.
+
+![Catastrophic Forgetting](plots/alignment_worst.png)

benchmark_results_meta_pretrain.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7916c730157224a6f72f8d60aff0c1d85f6ea5e86efe41e809c1e66e3f929b21
+size 14565

benchmark_results_zh_pretrain_multishot.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f697052882bb3e25d7c21f8e23f83ead3c57d63ab06151b1fd2b61165788aa1f
+size 483144

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:536db8dbb2eae8b6922e32ea3eba9d303422677e29f21e6049988173d932dfd7
+size 1217

evaluation_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3885e1161b8caa9d7fc15ada0297eccced2ab412529e28d9a139a101a1e5012
+size 272

generation_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876653772dee958707f51e8a0aebd2a6ec7f3e3cbc1d35986a55b9134814ccbe
+size 143

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3da6a639ee54a080233f00599f656ae4f20fac5648e4f5371d190a3f241d3da
+size 4976660480

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da14a1f7573e82c206341761cbf8ab9cf8104e707706fbba42aef6b8f3f819b7
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111cb952aafc85e16e97fea6582f456058049d5c41854c7d951009fdf61c6017
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:805698261ddf30b477e262172b4c40e011f67d7d948a6850741431b49bb410ec
+size 1168155192

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e675e9f23a294baff7e3a614ae39e4cef7f2b7aef18cf8baf18515eec29ef1
+size 23950

special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602e9a79a0ea636f1a1aafdc524ee6919d17b1c5c737d81332b1aaf5927122cf
+size 577

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a200d62d1a1177908f4310d7e367f0194d474db0038dc1f2f2434a3ef74af7d9
+size 17210284

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db3384732a446ad1fb56b15ec603920b13f148d7be21cda2c67857a9b7afe61
+size 50969