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 10, 2025

Commit

c4c3925

verified ·

1 Parent(s): 0125761

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -5

README.md CHANGED Viewed

@@ -90,21 +90,21 @@ The plot below highlights the alignment comparison of the model trained with Con
 ### Benchmark Results Table
 The table below summarizes the evaluation results across mathematical tasks and original capabilities.
-| **Model**         | **MathH** | **Math** | **GSM8K** | **Math Avg.** | **ARC** | **GPQA** | **MMLU** | **MMLUP** | **Orig. Avg.** | **Overall** |
 |-------------------|-----------|----------|-----------|---------------|---------|----------|----------|-----------|----------------|-------------|
 | Llama3.1-8B-Inst  | 23.7      | 50.9     | 85.6      | 52.1          | 83.4    | 29.9     | 72.4     | 46.7      | 60.5           | 56.3        |
 | OpenMath2-Llama3  | 38.4      | 64.1     | 90.3      | 64.3          | 45.8    | 1.3      | 4.5      | 19.5      | 12.9           | 38.6        |
 | **Full Tune**      | **38.5**  | **63.7** | 90.2      | **63.9**      | 58.2    | 1.1      | 7.3      | 23.5      | 16.5           | 40.1        |
 | Partial Tune      | 36.4      | 61.4     | 89.0      | 61.8          | 66.2    | 6.0      | 25.7     | 30.9      | 29.3           | 45.6        |
-| Stack Expansion   | 35.6      | 61.0     | 90.8      | 61.8          | 69.3    | 18.8     | 61.8     | 43.1      | 53.3           | 57.6        |
-| Hybrid Expansion  | 34.4      | 61.1     | 90.1      | 61.5          | **81.8**| **25.9** | 67.2     | **43.9**  | 57.1           | 59.3        |
 | **Control LLM***   | 38.1      | 62.7     | **90.4**  | 63.2          | 79.7    | 25.2     | **68.1** | 43.6      | **57.2**       | **60.2**    |
 ---
 ### Explanation of Metrics
-- **MathH**: MathHard
-- **Math**: General math reasoning
 - **GSM8K**: Grade-school math
 - **Math Avg.**: Average performance across Math Hard, Math, and GSM8K
 - **ARC**: AI reasoning challenge

 ### Benchmark Results Table
 The table below summarizes the evaluation results across mathematical tasks and original capabilities.
+| **Model**         | **MH** | **M** | **GSM8K** | **Math Avg.** | **ARC** | **GPQA** | **MMLU** | **MMLUP** | **Orig. Avg.** | **Overall** |
 |-------------------|-----------|----------|-----------|---------------|---------|----------|----------|-----------|----------------|-------------|
 | Llama3.1-8B-Inst  | 23.7      | 50.9     | 85.6      | 52.1          | 83.4    | 29.9     | 72.4     | 46.7      | 60.5           | 56.3        |
 | OpenMath2-Llama3  | 38.4      | 64.1     | 90.3      | 64.3          | 45.8    | 1.3      | 4.5      | 19.5      | 12.9           | 38.6        |
 | **Full Tune**      | **38.5**  | **63.7** | 90.2      | **63.9**      | 58.2    | 1.1      | 7.3      | 23.5      | 16.5           | 40.1        |
 | Partial Tune      | 36.4      | 61.4     | 89.0      | 61.8          | 66.2    | 6.0      | 25.7     | 30.9      | 29.3           | 45.6        |
+| Stack Exp.   | 35.6      | 61.0     | 90.8      | 61.8          | 69.3    | 18.8     | 61.8     | 43.1      | 53.3           | 57.6        |
+| Hybrid Exp.n  | 34.4      | 61.1     | 90.1      | 61.5          | **81.8**| **25.9** | 67.2     | **43.9**  | 57.1           | 59.3        |
 | **Control LLM***   | 38.1      | 62.7     | **90.4**  | 63.2          | 79.7    | 25.2     | **68.1** | 43.6      | **57.2**       | **60.2**    |
 ---
 ### Explanation of Metrics
+- **MH**: MathHard
+- **M**: Math - General math reasoning
 - **GSM8K**: Grade-school math
 - **Math Avg.**: Average performance across Math Hard, Math, and GSM8K
 - **ARC**: AI reasoning challenge