Instructions to use ControlLLM/Llama3.1-8B-OpenMath16-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ControlLLM/Llama3.1-8B-OpenMath16-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="ControlLLM/Llama3.1-8B-OpenMath16-Instruct")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ControlLLM/Llama3.1-8B-OpenMath16-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ControlLLM/Llama3.1-8B-OpenMath16-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ControlLLM/Llama3.1-8B-OpenMath16-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/Llama3.1-8B-OpenMath16-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ControlLLM/Llama3.1-8B-OpenMath16-Instruct

SGLang

How to use ControlLLM/Llama3.1-8B-OpenMath16-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/Llama3.1-8B-OpenMath16-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/Llama3.1-8B-OpenMath16-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/Llama3.1-8B-OpenMath16-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/Llama3.1-8B-OpenMath16-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ControlLLM/Llama3.1-8B-OpenMath16-Instruct with Docker Model Runner:
```
docker model run hf.co/ControlLLM/Llama3.1-8B-OpenMath16-Instruct
```

hawei commited on Jan 9, 2025

Commit

d114d94

verified ·

1 Parent(s): 1cfd3f7

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -13,9 +13,9 @@ model-index:
       type: math-evaluation
     dataset:
       type: parquet
-      name: OpenMathInstruct
       dataset_kwargs:
-        data_files: "/home/jobuser/controlllm/inference/llm_eval_harness/additional_tasks/math/joined_math.parquet"
     metrics:
     - name: exact_match,none
       type: exact_match
@@ -40,8 +40,8 @@ model-index:
   - task:
       type: original-capability
     dataset:
-      type: meta/arc-dataset
-      name: Meta-ARC Dataset
       dataset_path: "meta-llama/llama-3.1-8_b-instruct-evals"
       dataset_name: "Llama-3.1-8B-Instruct-evals__arc_challenge__details"
     metrics:

       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
   - 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: