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 +1,114 @@
 ---
 license: llama3.1
+datasets:
+- nvidia/OpenMathInstruct-2
+language:
+- en
+base_model:
+- meta-llama/Llama-3.1-8B-Instruct
+model-index:
+- name: Control-LLM-Llama3.1-8B-Math16
+  results:
+  - task:
+      type: code-evaluation
+    dataset:
+      type: mixed
+      name: Code Evaluation Dataset
+    metrics:
+    - name: pass_at_1,n=1 (code_instruct)
+      type: pass_at_1
+      value: 0.7840083073727934
+      stderr: 0.013257237506304915
+      verified: false
+    - name: pass_at_1,n=1 (humaneval_greedy_instruct)
+      type: pass_at_1
+      value: 0.8170731707317073
+      stderr: 0.03028135999593353
+      verified: false
+    - name: pass_at_1,n=1 (humaneval_plus_greedy_instruct)
+      type: pass_at_1
+      value: 0.7439024390243902
+      stderr: 0.03418746588364997
+      verified: false
+    - name: pass_at_1,n=1 (mbpp_plus_0shot_instruct)
+      type: pass_at_1
+      value: 0.8042328042328042
+      stderr: 0.0204357309715418
+      verified: false
+    - name: pass_at_1,n=1 (mbpp_sanitized_0shot_instruct)
+      type: pass_at_1
+      value: 0.7587548638132295
+      stderr: 0.02673991635681605
+      verified: false
+  - task:
+      type: original-capability
+    dataset:
+      type: meta/Llama-3.1-8B-Instruct-evals
+      name: Llama-3.1-8B-Instruct-evals Dataset
+      dataset_path: "meta-llama/llama-3.1-8_b-instruct-evals"
+      dataset_name: "Llama-3.1-8B-Instruct-evals__arc_challenge__details"
+    metrics:
+    - name: exact_match,strict-match (original_capability_instruct)
+      type: exact_match
+      value: 0.5630801459168563
+      stderr: 0.0028483348465514185
+      verified: false
+    - name: exact_match,strict-match (meta_arc_0shot_instruct)
+      type: exact_match
+      value: 0.8248927038626609
+      stderr: 0.01113972223585952
+      verified: false
+    - name: exact_match,strict-match (meta_gpqa_0shot_cot_instruct)
+      type: exact_match
+      value: 0.296875
+      stderr: 0.021609729061250887
+      verified: false
+    - name: exact_match,strict-match (meta_mmlu_0shot_instruct)
+      type: exact_match
+      value: 0.6815980629539952
+      stderr: 0.003931452244804845
+      verified: false
+    - name: exact_match,strict-match (meta_mmlu_pro_5shot_instruct)
+      type: exact_match
+      value: 0.4093251329787234
+      stderr: 0.004482884901882547
+      verified: false
 ---
+# Control-LLM-Llama3.1-8B-Math16
+This is a fine-tuned model of Llama-3.1-8B-Instruct for mathematical tasks on OpenCoder SFT dataset.
+
+## Evaluation Results
+Here is an overview of the evaluation results and findings:
+
+### Benchmark Result and Catastrophic Forgetting on OpenCoder
+The following plot illustrates benchmark result and catastrophic forgetting mitigation on the OpenCoder SFT dataset.
+
+![Catastrophic Forgetting](plots/catastrophic_forgetting_opencoder.png)
+
+### Benchmark Results Table
+The table below summarizes evaluation results across coding tasks and original capabilities.
+
+| **Model**          | **MB+** | **MS**  | **HE+** | **HE**  | **C-Avg** | **ARC** | **GP**  | **MLU** | **MLUP** | **O-Avg** | **Overall** |
+|--------------------|---------|---------|---------|---------|-----------|---------|---------|---------|----------|-----------|-------------|
+| Llama3.1-8B-Ins   | 70.4    | 67.7    | 66.5    | 70.7    | 69.1      | 83.4    | 29.9    | 72.4    | 46.7     | 60.5      | 64.8        |
+| OpenCoder-8B-Ins  | 81.2    | 76.3    | 78.0    | 82.3    | 79.5      | 8.2     | 25.4    | 37.4    | 11.3     | 24.6      | 52.1        |
+| **Full Param Tune**| 75.1    | 69.6    | 71.3    | 76.8    | 73.3      | 24.4    | 21.9    | 43.0    | 19.2     | 31.5      | 52.4        |
+| Partial Param Tune | 75.7    | 71.6    | 74.4    | 79.3    | 75.0      | 70.2    | 28.1    | 60.7    | 32.4     | 48.3      | 61.7        |
+| Stack Expansion    | 77.2    | 72.8    | 73.2    | 78.7    | 75.6      | 80.0    | 26.3    | 66.6    | 38.2     | 54.2      | 64.9        |
+| Hybrid Expansion*  | 77.5    | 73.5    | **76.2**| **82.3**| 77.1      | 80.9    | **32.6**| 68.1    | 40.3     | 56.0      | 66.6        |
+| **Control LLM***   | **80.4**| **75.9**| 74.4    | 81.1    | **78.3**  | **82.5**| 29.7    | **68.2**| **40.9** | **56.3**  | **67.3**    |
+
+---
+
+### Explanation:
+- **MB+**: MBPP Plus
+- **MS**: MBPP Sanitized
+- **HE+**: HumanEval Plus
+- **HE**: HumanEval
+- **C-Avg**: Coding - Size Weighted Average across MB+, MS, HE+, and HE
+- **ARC**: ARC benchmark
+- **GP**: GPQA benchmark
+- **MLU**: MMLU (Massive Multitask Language Understanding)
+- **MLUP**: MMLU Pro
+- **O-Avg**: Original Capability - Size Weighted Average across ARC, GPQA, MMLU, and MMLU Pro
+- **Overall**: Combined average across all tasks

benchmark_results_code_instruct.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6199e12ee08cddf074ddb4712b39440e8be166bd99d45eeec1e7050b3252aea
+size 18321

benchmark_results_original_capability_instruct.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b236479e2183f37eae7caef1adce93f20147ac2be478c8ffc893a42583b6c699
+size 17231

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3ac4fc4f51ac8ae6a23d7425533c9ce7a91c5b5a7eda80c2909f0b56336fc01
+size 1747

evaluation_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4a88dc174e1604af1e83f0d6d13c71862a65e9bf646511270a3d9f141b2ee4
+size 921

generation_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3dea9cdfa4a3e0edf1b52d9b1e9609aa22efcddce630060b748284663c8e67
+size 177

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f918e91dec283d291d864aaa45d69ffec7a757c4eb47e0b028d0034e6b9268
+size 4976765742

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44f2bf1cf8eddf0c3b76952a4ec902ceffffe1fdad84766fee02acd585252dde
+size 4999853582

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928b8ee9f7f26f1ab43be8e36f1bbcdb0b5b2c127bf94585180c2dd30cd11311
+size 4915983640

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4218fea139ca82ff487a993df7323a28c367c27f9920013753e420036e694b12
+size 4999886888

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a1674c2c65e088709514f377d59d691c1454bcdfcfb875f820fadb2e9512009
+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 sha256:453db79c09538b7953c4d9846d4bc0b46b86a296f285cdecc29f739f0b98f6a9
+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