Instructions to use ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct

SGLang

How to use ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct with Docker Model Runner:
```
docker model run hf.co/ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct
```

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.

Linked Open Source code - training, eval and benchmark

This model is associated with the github: Control-LLM.

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.

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

Downloads last month: 9

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Finetuned

(2732)

this model

Dataset used to train ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct

Paper for ControlLLM/Llama-3.1-8B-OpenCoder16-Instruct

Control LLM: Controlled Evolution for Intelligence Retention in LLM

Paper • 2501.10979 • Published Jan 19, 2025 • 6

Evaluation results

pass_at_1,n=1 (code_instruct) on Code Evaluation Dataset
self-reported

0.784
pass_at_1,n=1 (humaneval_greedy_instruct) on Code Evaluation Dataset
self-reported

0.817
pass_at_1,n=1 (humaneval_plus_greedy_instruct) on Code Evaluation Dataset
self-reported

0.744
pass_at_1,n=1 (mbpp_plus_0shot_instruct) on Code Evaluation Dataset
self-reported

0.804
pass_at_1,n=1 (mbpp_sanitized_0shot_instruct) on Code Evaluation Dataset
self-reported

0.759
exact_match,strict-match (original_capability_instruct) on Llama-3.1-8B-Instruct-evals Dataset
self-reported

0.563
exact_match,strict-match (meta_arc_0shot_instruct) on Llama-3.1-8B-Instruct-evals Dataset
self-reported

0.825
exact_match,strict-match (meta_gpqa_0shot_cot_instruct) on Llama-3.1-8B-Instruct-evals Dataset
self-reported

0.297
exact_match,strict-match (meta_mmlu_0shot_instruct) on Llama-3.1-8B-Instruct-evals Dataset
self-reported

0.682
exact_match,strict-match (meta_mmlu_pro_5shot_instruct) on Llama-3.1-8B-Instruct-evals Dataset
self-reported

0.409