config.json

{
  "_name_or_path": "de-coder/UlizaLlama_Q4_K_M-gguf",
  "architectures": ["LlamaForCausalLM"],
  "model_type": "llama",
  "torch_dtype": "float16",
  "transformers_version": "4.34.0",
  
  "vocab_size": 20000,
  "hidden_size": 4096,
  "intermediate_size": 11008,
  "num_hidden_layers": 32,
  "num_attention_heads": 32,
  "num_key_value_heads": 32,
  "hidden_act": "silu",
  "max_position_embeddings": 4096,
  "initializer_range": 0.02,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000.0,
  "rope_scaling": null,
  "attention_bias": false,
  "use_cache": true,
  "tie_word_embeddings": false,
  
  "bos_token_id": 1,
  "eos_token_id": 2,
  "pad_token_id": 0,
  "unk_token_id": 0,
  
  "quantization": {
    "method": "GGUF",
    "bits": 4,
    "variant": "q4_0",
    "block_size": 32,
    "group_size": 32,
    "tensors": {
      "query": "Q4_0",
      "key": "Q4_0",
      "value": "Q4_0",
      "output": "Q4_0",
      "intermediate": "Q4_0",
      "gate": "Q4_0",
      "embedding": "Q4_0",
      "norm": "F16"
    },
    "scales_dtype": "fp16"
  },
  
  "tokenizer": {
    "type": "BPE",
    "vocab_file": "ulizallama-tokenizer.json",
    "merges_file": "ulizallama-merges.txt"
  },
  
  "generation": {
    "temperature": 0.7,
    "top_p": 0.95,
    "top_k": 40,
    "repetition_penalty": 1.1,
    "max_new_tokens": 512
  },
 
  "base_model": {
    "name": "Jacaranda/kiswallama-pretrained",
    "type": "Llama2 Continual Pretraining"
  },
  "quantization_process": {
    "library": "llama.cpp",
    "version": "1.0.0",
    "command": "llama.cpp quantize ulizallama-7b.gguf ulizallama-7b-gguf-q4_0.bin q4_0"
  }
}