upload model 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 +1,110 @@
 ---
 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: math-evaluation
+    dataset:
+      type: parquet
+      name: Math, Math Hard, GSM8K
+      dataset_kwargs:
+        data_files: "https://github.com/linkedin/ControlLLM/blob/main/src/controlllm/inference/llm_eval_harness/additional_tasks/math/joined_math.parquet"
+    metrics:
+    - name: exact_match,none
+      type: exact_match
+      value: 0.6205678398534606
+      stderr: 0.005249520342473376
+      verified: false
+    - name: exact_match,none (gsm8k_0shot_instruct)
+      type: exact_match
+      value: 0.8968915845337376
+      stderr: 0.008376436987507811
+      verified: false
+    - name: exact_match,none (meta_math_0shot_instruct)
+      type: exact_match
+      value: 0.6166
+      stderr: 0.006876797660918556
+      verified: false
+    - name: exact_match,none (meta_math_hard_0shot_instruct)
+      type: exact_match
+      value: 0.36027190332326287
+      stderr: 0.013198755610252931
+      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
+      type: exact_match
+      value: 0.6001372485281902
+      stderr: 0.002821514831773572
+      verified: false
+    - name: exact_match,strict-match (meta_arc_0shot_instruct)
+      type: exact_match
+      value: 0.8248927038626609
+      stderr: 0.011139722235859526
+      verified: false
+    - name: exact_match,strict-match (meta_gpqa_0shot_cot_instruct)
+      type: exact_match
+      value: 0.3080357142857143
+      stderr: 0.021836780796366417
+      verified: false
+    - name: exact_match,strict-match (meta_mmlu_0shot_instruct)
+      type: exact_match
+      value: 0.7159948725252813
+      stderr: 0.00380556397209409
+      verified: false
+    - name: exact_match,strict-match (meta_mmlu_pro_5shot_instruct)
+      type: exact_match
+      value: 0.45403922872340424
+      stderr: 0.004539171007529716
+      verified: false
 ---
+# Control-LLM-Llama3.1-8B-Math16
+This is a fine-tuned model of Llama-3.1-8B-Instruct for mathematical tasks on OpenMath2 dataset.
+
+## Evaluation Results
+Here is an overview of the evaluation results and findings:
+
+### Catastrophic Forgetting on OpenMath
+The following plot illustrates and compares catastrophic forgetting mitigation during training
+
+![Catastrophic Forgetting](plots/ControlLLM_CF_Plot_Math.png)
+
+### Alignment Result
+The plot below highlights the alignment result of the model trained with Control LLM.
+
+![Alignment](plots/alignment_best.png)
+
+### Benchmark Results Table
+The table below summarizes evaluation results across mathematical tasks and original capabilities.
+
+| **Model**         | **MH** | **M**  | **G8K** | **M-Avg** | **ARC** | **GPQA** | **MLU** | **MLUP** | **O-Avg** | **Overall** |
+|-------------------|--------|--------|---------|-----------|---------|----------|---------|----------|-----------|-------------|
+| Llama3.1-8B-Inst  | 23.7   | 50.9   | 85.6    | 52.1      | 83.4    | 29.9     | 72.4    | 46.7     | 60.5      | 56.3        |
+| **Control LLM***   | 36.0   | 61.7   | **89.7**| 62.5      | 82.5    | 30.8     | **71.6**| 45.4     | **57.6**  | **60.0**    |
+
+---
+
+### Explanation:
+- **MH**: MathHard
+- **M**: Math
+- **G8K**: GSM8K
+- **M-Avg**: Math - Average across MathHard, Math, and GSM8K
+- **ARC**: ARC benchmark
+- **GPQA**: General knowledge QA
+- **MLU**: MMLU (Massive Multitask Language Understanding)
+- **MLUP**: MMLU Pro
+- **O-Avg**: Original Capability - Average across ARC, GPQA, MMLU, and MLUP
+- **Overall**: Combined average across all tasks

benchmark_results_code_instruct_mbpp_full_instruct_mbpp_full_0shot_instruct.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73f28e47a94ecdea8ddfc31a400bd998545805e536d380d5e27be89c127a85d2
+size 25067

benchmark_results_math_instruct.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f5ecb155cb0d90f3a674cda875595d0f82875469efaf2ada59b68a476ce682
+size 19758

benchmark_results_meta_mmlu_0shot_instruct_meta_math_hard_0shot.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e76a91f6132c6bc67f61b4f20811be17804c2c63d097609207dd72717ce64f32
+size 8220

benchmark_results_original_capability_instruct.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fcca219b2d813ae896863459df232a375ee9839d9619300362b6350fc2c5df2
+size 17088

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da07d008c75f7dce2f45183c9d5782cdac604434fc8ce7a5f3a8a2652a57b2d
+size 1900

evaluation_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b69a2e19dc8a0f499c05a03b44e85d4835e4676e111cf0b021389e638976058
+size 474

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dffb3a2cc9aedf7ab9d572cd4556c3341a268a4dd7dcd2f7f7c57554bb222eb
+size 4976715708

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e788da6d01317d0bfe87fe87f37757f9676339f5e823ab9670d2263ab70597d
+size 4999803628

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6dbb9f45d938bd005593c3a56f86e623035eebcc55c30ea855d5821c5afb00
+size 4915916972

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9719edbfeb2b6a7d2be2e95257c8a1e67e385d63c968df2d76c64172c83df9fa
+size 4657956396

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9c8d1f60f3aa192fa8cd45f480271fcb13050fac1c8214de4e049759ae32fd
+size 32818

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