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 +1,107 @@
 ---
 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
+model-index:
+- name: Control-LLM-Llama3.1-8B-SynE-Concat16-Lerp
+  results:
+  - task:
+      type: pretraining-evaluation
+    dataset:
+      type: mixed
+      name: Pretraining Evaluation Dataset
+    metrics:
+    - name: exact_match,strict-match (meta_pretrain)
+      type: exact_match
+      value: 0.458555789246616
+      stderr: 0.003519105746208811
+      verified: false
+    - name: exact_match,strict-match (meta_bbh_3shot_cot_pretrain)
+      type: exact_match
+      value: 0.6442942712332975
+      stderr: 0.005933310420690264
+      verified: false
+    - name: acc,none (meta_mmlu_5shot_pretrain)
+      type: accuracy
+      value: 0.6464178891895741
+      stderr: 0.004034621567546711
+      verified: false
+    - name: exact_match,strict-match (meta_mmlu_pro_5shot_pretrain)
+      type: exact_match
+      value: 0.35804521276595747
+      stderr: 0.004370894189453768
+      verified: false
+  - task:
+      type: chinese-evaluation
+    dataset:
+      type: mixed
+      name: Chinese Evaluation Dataset
+    metrics:
+    - name: exact_match,strict-match (zh_pretrain_multishot)
+      type: exact_match
+      value: 0.37105507425742573
+      stderr: 0.004143191283994466
+      verified: false
+    - name: acc,none (ceval-valid)
+      type: accuracy
+      value: 0.5713224368499257
+      stderr: 0.01292052444857274
+      verified: false
+    - name: exact_match,strict-match (ceval-valid-pretrain-cot_zh)
+      type: exact_match
+      value: 0.34843982169390786
+      stderr: 0.01265919137729175
+      verified: false
+    - name: acc,none (cmmlu)
+      type: accuracy
+      value: 0.5689000172681747
+      stderr: 0.004489346390434928
+      verified: false
+    - name: exact_match,strict-match (cmmlu_pretrain_cot_zh)
+      type: exact_match
+      value: 0.37368330167501296
+      stderr: 0.00438421288652232
+      verified: false
 ---
+# Control-LLM-Llama3.1-8B-SynE-Concat16-Lerp
+This is a fine-tuned model of Llama-3.1-8B for muliligual-Chinese tasks on SynE dataset by Control LLM-Concat16-Lerp.
+
+## 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

benchmark_results_meta_pretrain.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4070c146cba1b8692220960b10d63f752553fe58c0df1db76cf0fa1ad473b6d3
+size 14647

benchmark_results_zh_pretrain_multishot.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8fb99b7d805bc478e5edf9002a62b938e94e8d09ff438f36ae2c0cb983122d
+size 483361

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f6665c498780668dd1716b274a0e58ae2bdb23d59671a434069d5b950d2889
+size 1862

evaluation_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94028103cee95f7798eea7e614bdd6ab894b80c485b09df5f022f3ad21655ec9
+size 669

generation_config.json

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

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42cce424efbd6a95ea07cccb17cef1dd48284192b235a6a0f4c74dc878dbab7
+size 4976716246

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c85bc4a49bf9d4ec95b3b2f97da029ca3b5eded93d55833cc831d97e159a9c
+size 4999804192

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53eaf2fad4b0cd15790b77dcb8a460b736ddb5f81eaa3e1baf2eedc626ce7080
+size 4915917640

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6371ba57a5a37ae60862b34d8ad49387e7686f2508823a297455d860e954c5c6
+size 4999820896

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cfbfb7a5dce8c102363166b0cc555ef46d2e42c29120d216b633978fc504783
+size 3147937266

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eebd7862a88227b21730c4862a26eb90c871c2f6c873e14a7cf9598d9771a21e
+size 41676

special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453db79c09538b7953c4d9846d4bc0b46b86a296f285cdecc29f739f0b98f6a9
+size 572

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 sha256:9e407a45cd60fbcdad88f1a22adab70157c47e858c0c94995de05e87b06205aa
+size 55820