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

[
  {
    "sources": [
      {
        "filename": "config.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/LlamaCorn-1.1B-Chat-fp16/config.json"
      },
      {
        "filename": "mistral_float16_tp1_rank0.engine",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/LlamaCorn-1.1B-Chat-fp16/mistral_float16_tp1_rank0.engine"
      },
      {
        "filename": "tokenizer.model",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/LlamaCorn-1.1B-Chat-fp16/tokenizer.model"
      },
      {
        "filename": "special_tokens_map.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/LlamaCorn-1.1B-Chat-fp16/special_tokens_map.json"
      },
      {
        "filename": "tokenizer.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/LlamaCorn-1.1B-Chat-fp16/tokenizer.json"
      },
      {
        "filename": "tokenizer_config.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/LlamaCorn-1.1B-Chat-fp16/tokenizer_config.json"
      },
      {
        "filename": "model.cache",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/LlamaCorn-1.1B-Chat-fp16/model.cache"
      }
    ],
    "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,
      "text_model": false
    },
    "parameters": {
      "max_tokens": 4096
    },
    "metadata": {
      "author": "LLama",
      "tags": ["TensorRT-LLM", "1B", "Finetuned"],
      "size": 2151000000
    },
    "engine": "nitro-tensorrt-llm"
  },
  {
    "sources": [
      {
        "filename": "config.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/TinyJensen-1.1B-Chat-fp16/config.json"
      },
      {
        "filename": "mistral_float16_tp1_rank0.engine",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/TinyJensen-1.1B-Chat-fp16/mistral_float16_tp1_rank0.engine"
      },
      {
        "filename": "tokenizer.model",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/TinyJensen-1.1B-Chat-fp16/tokenizer.model"
      },
      {
        "filename": "special_tokens_map.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/TinyJensen-1.1B-Chat-fp16/special_tokens_map.json"
      },
      {
        "filename": "tokenizer.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/TinyJensen-1.1B-Chat-fp16/tokenizer.json"
      },
      {
        "filename": "tokenizer_config.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/TinyJensen-1.1B-Chat-fp16/tokenizer_config.json"
      },
      {
        "filename": "model.cache",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/TinyJensen-1.1B-Chat-fp16/model.cache"
      }
    ],
    "id": "tinyjensen-1.1b-chat-fp16",
    "object": "model",
    "name": "TinyJensen 1.1B Chat FP16",
    "version": "1.0",
    "description": "Do you want to chat with Jensen Huan? Here you are",
    "format": "TensorRT-LLM",
    "settings": {
      "ctx_len": 2048,
      "text_model": false
    },
    "parameters": {
      "max_tokens": 4096
    },
    "metadata": {
      "author": "LLama",
      "tags": ["TensorRT-LLM", "1B", "Finetuned"],
      "size": 2151000000
    },
    "engine": "nitro-tensorrt-llm"
  },
  {
    "sources": [
      {
        "filename": "config.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/Mistral-7B-Instruct-v0.1-int4/config.json"
      },
      {
        "filename": "mistral_float16_tp1_rank0.engine",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/Mistral-7B-Instruct-v0.1-int4/mistral_float16_tp1_rank0.engine"
      },
      {
        "filename": "tokenizer.model",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/Mistral-7B-Instruct-v0.1-int4/tokenizer.model"
      },
      {
        "filename": "special_tokens_map.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/Mistral-7B-Instruct-v0.1-int4/special_tokens_map.json"
      },
      {
        "filename": "tokenizer.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/Mistral-7B-Instruct-v0.1-int4/tokenizer.json"
      },
      {
        "filename": "tokenizer_config.json",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/Mistral-7B-Instruct-v0.1-int4/tokenizer_config.json"
      },
      {
        "filename": "model.cache",
        "url": "https://delta.jan.ai/dist/models/<gpuarch>/<os>/tensorrt-llm-v0.7.1/Mistral-7B-Instruct-v0.1-int4/model.cache"
      }
    ],
    "id": "mistral-7b-instruct-int4",
    "object": "model",
    "name": "Mistral 7B Instruct v0.1 INT4",
    "version": "1.0",
    "description": "Mistral 7B Instruct v0.1 INT4",
    "format": "TensorRT-LLM",
    "settings": {
      "ctx_len": 2048,
      "text_model": false,
      "prompt_template": "[INST] {prompt} [/INST]"
    },
    "parameters": {
      "max_tokens": 4096
    },
    "metadata": {
      "author": "MistralAI",
      "tags": ["TensorRT-LLM", "7B", "Finetuned"],
      "size": 3840000000
    },
    "engine": "nitro-tensorrt-llm"
  }
]