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-Hybrid
+  results:
+  - task:
+      type: pretraining-evaluation
+    dataset:
+      type: mixed
+      name: Pretraining Evaluation Dataset
+    metrics:
+    - name: exact_match,strict-match (meta_pretrain)
+      type: exact_match
+      value: 0.4677775980154236
+      stderr: 0.0035271375539740195
+      verified: false
+    - name: exact_match,strict-match (meta_bbh_3shot_cot_pretrain)
+      type: exact_match
+      value: 0.6516664106896022
+      stderr: 0.005904999312183116
+      verified: false
+    - name: acc,none (meta_mmlu_5shot_pretrain)
+      type: accuracy
+      value: 0.6574562028201111
+      stderr: 0.004004907112115045
+      verified: false
+    - name: exact_match,strict-match (meta_mmlu_pro_5shot_pretrain)
+      type: exact_match
+      value: 0.36826795212765956
+      stderr: 0.004397416024070344
+      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: 0.4448483910891089
+      stderr: 0.004279257037413458
+      verified: false
+    - name: acc,none (ceval-valid)
+      type: accuracy
+      value: 0.5891530460624071
+      stderr: 0.012995719777231915
+      verified: false
+    - name: exact_match,strict-match (ceval-valid-pretrain-cot_zh)
+      type: exact_match
+      value: 0.44650817236255574
+      stderr: 0.013132438471522461
+      verified: false
+    - name: acc,none (cmmlu)
+      type: accuracy
+      value: 0.578742876877914
+      stderr: 0.004459355253649275
+      verified: false
+    - name: exact_match,strict-match (cmmlu_pretrain_cot_zh)
+      type: exact_match
+      value: 0.4446554999136591
+      stderr: 0.004526020080338497
+      verified: false
 ---
+# Control-LLM-Llama3.1-8B-SynE-Hybrid
+This is a fine-tuned model of Llama-3.1-8B for muliligual-Chinese tasks on SynE dataset by Control LLM-Hybrid.
+
+## 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:f557b7e7d791f99c032cb314a22b030c2540e59f70c9f67985469095c673cda8
+size 14640

benchmark_results_zh_pretrain_multishot.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a544f1434518b1ace1a3e0b8cadfb021ac350c5a09f4731974a3bdfb430b0b9
+size 483259

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:231d4bd247f0e3903f01e031f44a67be8ab3a3f3e9c7b524619c6219774110a2
+size 1934

evaluation_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f94ffaf769e93f6a75f0b2012dd1e794cce9f2ef7427923d64c19675c7e506d
+size 542

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 sha256:751beba17dfee0156ccc2e691e7b1aaba8dfda0a860c7210373cd83e4d478fde
+size 4976731946

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885753b638d3608f0ed5f933762c4f8e3fddb6357145bbaf16497dc3413508bc
+size 4999836492

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe097157ff23c1f2cfb005c652c6f8cbce9490ce136c4393aab716f241738bee
+size 4915949972

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a76ae44250b48b56a4bdf9dc925539c6e1fb6342c4db6767814efb1df4677ce
+size 4999853132

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f3481b0c969e60c509fe2f83d3f5dd6cf108f46a23722223288881b889c53d
+size 3147953546

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eb24dd431de61e23727f0473fdcf08071c64906661578c5376684060f5e3a34
+size 39432

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