| version: 1 | |
| modelName: TinyLlama | |
| license: apache-2.0 | |
| author: TinyLlama | |
| description: ... | |
| tags: | |
| default: | |
| llamacpp: 1.1b-chat-v1.0-gguf-Q4_K_M | |
| tensorrt-llm: | |
| ada: 1.1b-chat-v1.0-tensorrtllm-windows-ada-fp16 | |
| turing: 1.1b-chat-v1.0-tensorrtllm-windows-turing-fp16 | |
| ampere: 1.1b-chat-v1.0-tensorrtllm-windows-ampere-fp16 |