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-Dlerp
+  results:
+  - task:
+      type: pretraining-evaluation
+    dataset:
+      type: mixed
+      name: Pretraining Evaluation Dataset
+    metrics:
+    - name: exact_match,strict-match (meta_pretrain)
+      type: exact_match
+      value: 0.48514264142803215
+      stderr: 0.003513307445696379
+      verified: false
+    - name: exact_match,strict-match (meta_bbh_3shot_cot_pretrain)
+      type: exact_match
+      value: 0.6817693134695131
+      stderr: 0.0057729694388110805
+      verified: false
+    - name: acc,none (meta_mmlu_5shot_pretrain)
+      type: accuracy
+      value: 0.65596068936049
+      stderr: 0.0040090726054856874
+      verified: false
+    - name: exact_match,strict-match (meta_mmlu_pro_5shot_pretrain)
+      type: exact_match
+      value: 0.3787400265957447
+      stderr: 0.004422383756050139
+      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: 0.44848391089108913
+      stderr: 0.004255614019851072
+      verified: false
+    - name: acc,none (ceval-valid)
+      type: accuracy
+      value: 0.5698365527488856
+      stderr: 0.012893833892221353
+      verified: false
+    - name: exact_match,strict-match (ceval-valid-pretrain-cot_zh)
+      type: exact_match
+      value: 0.4472511144130758
+      stderr: 0.013203606600472227
+      verified: false
+    - name: acc,none (cmmlu)
+      type: accuracy
+      value: 0.5602659298912105
+      stderr: 0.0044928840587441605
+      verified: false
+    - name: exact_match,strict-match (cmmlu_pretrain_cot_zh)
+      type: exact_match
+      value: 0.4486271801070627
+      stderr: 0.00449553418468653
+      verified: false
 ---
+# Control-LLM-Llama3.1-8B-SynE-Concat16-Dlerp
+This is a fine-tuned model of Llama-3.1-8B for muliligual-Chinese tasks on SynE dataset by Control LLM-Concat16-Dlerp.
+
+## 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 sha256:957eed9985476a099b7b5738b1d02c49666409b5907b5a796e93b5d2ccbf7d34
+size 14610

benchmark_results_zh_pretrain_multishot.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b9e4573bcb3652b1c8a7a95770b6edc5e649103747ad39da691d4dc775530b
+size 483155

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc12636823e1e6ff7acfb8698c2712c0f9d628d6693a853d29bc22df4f68abda
+size 1844

evaluation_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c8d60f0b3789e5d342ab2f84086b5d0e583f0da8eeef926fd90b1f800e58d6
+size 908

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:aa0baa6a1e071002393e3380fdabe91d7bef24bb841495c80270f1c74c41aa8c
+size 4976765742

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de39882394f626ae3789c1d95b1936716e9c50b9574096f5ca83edc8451e1a36
+size 4999853582

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84240e28d6fa870611719fd57f970b33955754e2fa74925343b8a746e47fb822
+size 4915983640

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff910405f48bd10ab826d1f8cfc109e6993bbf2b3d439bf57b592ccf8689d8b5
+size 4999886888

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d7ca6873be8139841345af151e5068031d10e2342012ea81992066eba15b15
+size 3147970380

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a0746418bc2b35797d04c9fd6460fcf4e4de768b7aa9ab4b5f427b52099448
+size 43015

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