README.md

---
license: llama3.1
datasets:
- OpenCoder-LLM/opc-sft-stage1
- OpenCoder-LLM/opc-sft-stage2
language:
- en
base_model:
- meta-llama/Llama-3.1-8B-Instruct
model-index:
- name: Control-LLM-Llama3.1-8B-OpenCoder8
  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: 0.770508826583593
      stderr: 0.013547264970313243
      verified: false
    - name: pass_at_1,n=1 (humaneval_greedy_instruct)
      type: pass_at_1
      value: 0.823170731707317
      stderr: 0.029883277857485988
      verified: false
    - name: pass_at_1,n=1 (humaneval_plus_greedy_instruct)
      type: pass_at_1
      value: 0.7621951219512195
      stderr: 0.033346454086653404
      verified: false
    - name: pass_at_1,n=1 (mbpp_plus_0shot_instruct)
      type: pass_at_1
      value: 0.7751322751322751
      stderr: 0.02150209607822914
      verified: false
    - name: pass_at_1,n=1 (mbpp_sanitized_0shot_instruct)
      type: pass_at_1
      value: 0.7354085603112841
      stderr: 0.027569713464529938
      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: 0.5599378769819771
      stderr: 0.0028491774433443513
      verified: false
    - name: exact_match,strict-match (meta_arc_0shot_instruct)
      type: exact_match
      value: 0.8094420600858369
      stderr: 0.011511446994122106
      verified: false
    - name: exact_match,strict-match (meta_gpqa_0shot_cot_instruct)
      type: exact_match
      value: 0.32589285714285715
      stderr: 0.02216910313464341
      verified: false
    - name: exact_match,strict-match (meta_mmlu_0shot_instruct)
      type: exact_match
      value: 0.681241988320752
      stderr: 0.003932622311434926
      verified: false
    - name: exact_match,strict-match (meta_mmlu_pro_5shot_instruct)
      type: exact_match
      value: 0.4029255319148936
      stderr: 0.004471732136513382
      verified: false
pipeline_tag: text-generation
library_name: transformers
---

# Control-LLM-Llama3.1-8B-OpenCoder8
This is a fine-tuned model of Llama-3.1-8B-Instruct for coding tasks on OpenCoder SFT dataset described in the paper: [Control LLM: Controlled Evolution for Intelligence Retention in LLM](https://huggingface.co/papers/2501.10979).

Code: https://github.com/linkedin/ControlLLM.

## Evaluation Results
Here is an overview of the evaluation results and findings:

### Hybrid Expansion on OpenCoder
The following diagram illustrates how hybrid expansion works.

![Catastrophic Forgetting](plots/control_llm_structure_analysis.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        |
| **ControlLLM-Hybrid**  | 77.5    | 73.5    | **76.2**| **82.3**| 77.1      | 80.9    | **32.6**| 68.1    | 40.3     | 56.0      | 66.6        |

---

### 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