How to use from
vLLM
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vonjack/SmolLM2-360M-Merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vonjack/SmolLM2-360M-Merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'
Use Docker
docker model run hf.co/vonjack/SmolLM2-360M-Merged:Q8_0
Quick Links

SmolLM2-360M-Merged

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using HuggingFaceTB/SmolLM2-360M as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: HuggingFaceTB/SmolLM2-360M-Instruct
    parameters:
      weight: 1
merge_method: ties
base_model: HuggingFaceTB/SmolLM2-360M
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 7.13
IFEval (0-Shot) 32.06
BBH (3-Shot) 4.74
MATH Lvl 5 (4-Shot) 0.76
GPQA (0-shot) 0.78
MuSR (0-shot) 3.36
MMLU-PRO (5-shot) 1.09
Downloads last month
35
Safetensors
Model size
0.4B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for vonjack/SmolLM2-360M-Merged

Paper for vonjack/SmolLM2-360M-Merged

Evaluation results