qwen2.preset.json

{
  "name": "qwen2",
  "load_params": {
    "n_ctx": 1500,
    "n_batch": 512,
    "rope_freq_base": 0,
    "rope_freq_scale": 0,
    "n_gpu_layers": -1,
    "use_mlock": true,
    "main_gpu": 0,
    "tensor_split": [
      0
    ],
    "seed": -1,
    "f16_kv": true,
    "use_mmap": true
  },
  "inference_params": {
    "n_threads": 4,
    "n_predict": -1,
    "top_k": 40,
    "top_p": 0.95,
    "temp": 0.1,
    "repeat_penalty": 1.1,
    "input_prefix": "### Instruction:\\n",
    "input_suffix": "\\n### Response:\\n",
    "antiprompt": [
      "### Instruction:"
    ],
    "pre_prompt": "",
    "pre_prompt_suffix": "\\n",
    "pre_prompt_prefix": "",
    "seed": -1,
    "tfs_z": 1,
    "typical_p": 1,
    "repeat_last_n": 64,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "n_keep": 0,
    "logit_bias": {},
    "mirostat": 0,
    "mirostat_tau": 5,
    "mirostat_eta": 0.1,
    "memory_f16": true,
    "multiline_input": false,
    "penalize_nl": true,
    "min_p": 0.05
  }
}