llm-arch-research/experiments/llm_only/configs/mixtral_generate.json

{
    "bpe_tokenizer": "checkpoints/bpe_tokenizer.json",
    "test_prompts": [
      "Open weights",
      "The Llama model is",
      "Efficient transformers"
    ],
    "model_config_path": "checkpoints/mixtral-bpe/config.json",
    "model_weights": "checkpoints/mixtral-bpe/model.pt",
    "generation": {
      "max_new_tokens": 40,
      "temperature": 0.8,
      "do_sample": true,
      "top_k": null,
      "top_p": null
    },
    "log_path": "checkpoints/mixtral_only_generation_logs.json"
  }