Text Generation
Transformers
Safetensors
mixtral
Merge
mergekit
lazymergekit
text-generation-inference
TinyLlamaHerd-2x1.1B
TinyLlamaHerd-2x1.1B is a merge of the following models using mergekit:
🧩 Configuration
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
gate_mode: random
dtype: bfloat16
experts:
- source_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
positive_prompts: [""]
- source_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
positive_prompts: [""]
- Downloads last month
- 4
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "impossibleexchange/dip1"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "impossibleexchange/dip1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'