private-llm-config.json

{
  "model_type": "qwen2",
  "quantization": "GPTQ-Int4",
  "model_config": {
    "hidden_act": "silu",
    "hidden_size": 1536,
    "intermediate_size": 8960,
    "num_attention_heads": 12,
    "num_hidden_layers": 28,
    "num_key_value_heads": 2,
    "rms_norm_eps": 1e-06,
    "rope_theta": 1000000.0,
    "vocab_size": 151936,
    "tie_word_embeddings": true,
    "context_window_size": 8192,
    "prefill_chunk_size": 128,
    "tensor_parallel_shards": 1,
    "head_dim": 128,
    "dtype": "float32",
    "max_batch_size": 80
  },
  "vocab_size": 151936,
  "context_window_size": 8192,
  "sliding_window_size": -1,
  "prefill_chunk_size": 128,
  "attention_sink_size": -1,
  "tensor_parallel_shards": 1,
  "mean_gen_len": 128,
  "max_gen_len": 512,
  "shift_fill_factor": 0.3,
  "temperature": 0.7,
  "presence_penalty": 0.0,
  "frequency_penalty": 0.0,
  "repetition_penalty": 1.1,
  "top_p": 0.8,
  "conv_template": "qwen2",
  "pad_token_id": 151643,
  "bos_token_id": 151643,
  "eos_token_id": [
    151645,
    151643
  ],
  "tokenizer_files": [
    "tokenizer.json",
    "vocab.json",
    "merges.txt",
    "tokenizer_config.json"
  ],
  "version": "0.1.0"
}