Qwen1.5-1.8B-Chat-q4f16_1 / mlc-chat-config.json
hushell's picture
init (#1)
ecf9ee6 verified
{
"model_type": "qwen2",
"quantization": "q4f16_1",
"model_config": {
"hidden_act": "silu",
"hidden_size": 2048,
"intermediate_size": 5504,
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"vocab_size": 151936,
"context_window_size": 32768,
"prefill_chunk_size": 32768,
"tensor_parallel_shards": 1,
"dtype": "float32"
},
"vocab_size": 151936,
"context_window_size": 32768,
"sliding_window_size": -1,
"prefill_chunk_size": 32768,
"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": "chatml",
"pad_token_id": 0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"tokenizer_files": [
"tokenizer.json",
"vocab.json",
"merges.txt",
"tokenizer_config.json"
],
"version": "0.1.0"
}