Instructions to use aucson/llama3-code-math-regmean-merge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aucson/llama3-code-math-regmean-merge with Transformers:

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

pipe = pipeline("text-generation", model="aucson/llama3-code-math-regmean-merge")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aucson/llama3-code-math-regmean-merge")
model = AutoModelForCausalLM.from_pretrained("aucson/llama3-code-math-regmean-merge")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aucson/llama3-code-math-regmean-merge with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aucson/llama3-code-math-regmean-merge"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aucson/llama3-code-math-regmean-merge",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aucson/llama3-code-math-regmean-merge

SGLang

How to use aucson/llama3-code-math-regmean-merge 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 "aucson/llama3-code-math-regmean-merge" \
    --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": "aucson/llama3-code-math-regmean-merge",
		"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 "aucson/llama3-code-math-regmean-merge" \
        --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": "aucson/llama3-code-math-regmean-merge",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aucson/llama3-code-math-regmean-merge with Docker Model Runner:
```
docker model run hf.co/aucson/llama3-code-math-regmean-merge
```

aucson commited on Jun 10, 2025

Commit

130246f

verified ·

1 Parent(s): c06495c

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -3

README.md CHANGED Viewed

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
 ---
@@ -13,7 +15,7 @@ This repo is a fast and numerically stable re-implementation of RegMean model me
 We merge the following two models.
 - [Code Model] [rombodawg/rombos_Replete-Coder-Llama3-8B](https://huggingface.co/rombodawg/rombos_Replete-Coder-Llama3-8B) (Re-implementation of Replete-Coder)
-- [Math Model][ TIGER-Lab/MAmmoTH2-8B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B)
 ## Results
@@ -118,4 +120,4 @@ Here are other useful references that greatly inspired this re-implementation.
 [1] Yadav et al. 2024, [What Matters for Model Merging at Scale?](https://arxiv.org/abs/2410.03617)
-[2] Tam et al. 2024, [Merging by Matching Models in Task Parameter Subspaces](https://openreview.net/forum?id=qNGo6ghWFB)

 ---
 library_name: transformers
+base_model:
+- rombodawg/rombos_Replete-Coder-Llama3-8B
+- TIGER-Lab/MAmmoTH2-8B
 ---
 We merge the following two models.
 - [Code Model] [rombodawg/rombos_Replete-Coder-Llama3-8B](https://huggingface.co/rombodawg/rombos_Replete-Coder-Llama3-8B) (Re-implementation of Replete-Coder)
+- [Math Model] [TIGER-Lab/MAmmoTH2-8B](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B)
 ## Results
 [1] Yadav et al. 2024, [What Matters for Model Merging at Scale?](https://arxiv.org/abs/2410.03617)
+[2] Tam et al. 2024, [Merging by Matching Models in Task Parameter Subspaces](https://openreview.net/forum?id=qNGo6ghWFB)