jan/extensions/tensorrt-llm-extension/models.json

[
  {
    "sources": [
      {
        "filename": "config.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/LlamaCorn-1.1B-Chat-fp16/config.json"
      },
      {
        "filename": "rank0.engine",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/LlamaCorn-1.1B-Chat-fp16/rank0.engine"
      },
      {
        "filename": "tokenizer.model",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/LlamaCorn-1.1B-Chat-fp16/tokenizer.model"
      },
      {
        "filename": "special_tokens_map.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/LlamaCorn-1.1B-Chat-fp16/special_tokens_map.json"
      },
      {
        "filename": "tokenizer.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/LlamaCorn-1.1B-Chat-fp16/tokenizer.json"
      },
      {
        "filename": "tokenizer_config.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/LlamaCorn-1.1B-Chat-fp16/tokenizer_config.json"
      }
    ],
    "id": "llamacorn-1.1b-chat-fp16",
    "object": "model",
    "name": "LlamaCorn 1.1B Chat FP16",
    "version": "1.0",
    "description": "LlamaCorn is a refined version of TinyLlama-1.1B, optimized for conversational quality, running on consumer devices through TensorRT-LLM",
    "format": "TensorRT-LLM",
    "settings": {
      "ctx_len": 2048
    },
    "parameters": {
      "stream": true,
      "max_tokens": 4096
    },
    "metadata": {
      "author": "LLama",
      "tags": ["TensorRT-LLM", "1B", "Finetuned"],
      "size": 2151000000
    },
    "engine": "nitro-tensorrt-llm"
  }
]