README.md

---
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
library_name: transformers
pipeline_tag: text-generation
---

# 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.

## Linked Paper
This model is associated with the paper: [Control-LLM](https://arxiv.org/abs/2501.10979).

## Linked Open Source code - training, eval and benchmark
This model is associated with the github: [Control-LLM](https://github.com/linkedin/ControlLLM).

## 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