jeeves-mlx / config.json
cowWhySo's picture
Publish Jeeves MLX 4bit (CPU diagnostics; not benchmarked)
6f4220a verified
Raw History Blame Contribute Delete
2.08 kB
{
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 32,
"linear_value_head_dim": 128,
"max_position_embeddings": 262144,
"model_type": "qwen3_5",
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"pad_token_id": null,
"partial_rotary_factor": 0.25,
"quantization": {
"group_size": 64,
"bits": 4,
"mode": "affine"
},
"quantization_config": {
"group_size": 64,
"bits": 4,
"mode": "affine"
},
"rms_norm_eps": 1e-06,
"rope_parameters": {
"type": "default",
"rope_theta": 10000000,
"partial_rotary_factor": 0.25
},
"rope_theta": 10000000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"vocab_size": 248320
}