How to use from
vLLM
Install from pip and serve model
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Omni-Reasoner3-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": "prithivMLmods/Omni-Reasoner3-Merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'
Use Docker
docker model run hf.co/prithivMLmods/Omni-Reasoner3-Merged
Quick Links

omni.png

Merge Llama Based

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using prithivMLmods/Llama-Deepsync-3B 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: prithivMLmods/Llama-Magpie-3.2-3B-Instruct
  - model: prithivMLmods/Codepy-Deepthink-3B
  - model: prithivMLmods/Llama-Doctor-3.2-3B-Instruct
  - model: prithivMLmods/Llama-Sentient-3.2-3B-Instruct
  - model: prithivMLmods/Llama-Magpie-3.2-3B-Instruct
  - model: prithivMLmods/Llama-Deepsync-3B
merge_method: model_stock
base_model: prithivMLmods/Llama-Deepsync-3B
normalize: true
int8_mask: true
dtype: bfloat16
Downloads last month
26
Safetensors
Model size
3B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for prithivMLmods/Omni-Reasoner3-Merged

Collection including prithivMLmods/Omni-Reasoner3-Merged

Paper for prithivMLmods/Omni-Reasoner3-Merged