Instructions to use ControlLLM/Control-LLM-Llama3.1-8B-OpenCoder8-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ControlLLM/Control-LLM-Llama3.1-8B-OpenCoder8-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="ControlLLM/Control-LLM-Llama3.1-8B-OpenCoder8-Instruct")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ControlLLM/Control-LLM-Llama3.1-8B-OpenCoder8-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ControlLLM/Control-LLM-Llama3.1-8B-OpenCoder8-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ControlLLM/Control-LLM-Llama3.1-8B-OpenCoder8-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/Control-LLM-Llama3.1-8B-OpenCoder8-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ControlLLM/Control-LLM-Llama3.1-8B-OpenCoder8-Instruct

SGLang

How to use ControlLLM/Control-LLM-Llama3.1-8B-OpenCoder8-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/Control-LLM-Llama3.1-8B-OpenCoder8-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/Control-LLM-Llama3.1-8B-OpenCoder8-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/Control-LLM-Llama3.1-8B-OpenCoder8-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/Control-LLM-Llama3.1-8B-OpenCoder8-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ControlLLM/Control-LLM-Llama3.1-8B-OpenCoder8-Instruct with Docker Model Runner:
```
docker model run hf.co/ControlLLM/Control-LLM-Llama3.1-8B-OpenCoder8-Instruct
```

Add missing metadata

by nielsr HF Staff - opened Jan 25, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-4

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -74,12 +74,14 @@ model-index:
       value: 0.4029255319148936
       stderr: 0.004471732136513382
       verified: false
 ---
 # 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.
-## Linked Paper
-This model is associated with the paper: [Control-LLM](https://arxiv.org/abs/2501.10979).
 ## Evaluation Results
 Here is an overview of the evaluation results and findings:
@@ -114,4 +116,4 @@ The table below summarizes evaluation results across coding tasks and original c
 - **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

       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:
 - **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