95 lines
2.4 KiB
JSON
95 lines
2.4 KiB
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"Qwen3NextForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 151643,
|
||
|
|
"decoder_sparse_step": 1,
|
||
|
|
"eos_token_id": 151645,
|
||
|
|
"full_attention_interval": 4,
|
||
|
|
"head_dim": 256,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 2048,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 5120,
|
||
|
|
"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,
|
||
|
|
"mlp_only_layers": [],
|
||
|
|
"model_type": "qwen3_next",
|
||
|
|
"moe_intermediate_size": 512,
|
||
|
|
"norm_topk_prob": true,
|
||
|
|
"num_attention_heads": 16,
|
||
|
|
"num_experts": 512,
|
||
|
|
"num_experts_per_tok": 10,
|
||
|
|
"num_hidden_layers": 48,
|
||
|
|
"num_key_value_heads": 2,
|
||
|
|
"output_router_logits": false,
|
||
|
|
"partial_rotary_factor": 0.25,
|
||
|
|
"rms_norm_eps": 1e-06,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"rope_theta": 10000000,
|
||
|
|
"router_aux_loss_coef": 0.001,
|
||
|
|
"shared_expert_intermediate_size": 512,
|
||
|
|
"tie_word_embeddings": false,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.57.0.dev0",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_sliding_window": false,
|
||
|
|
"vocab_size": 151936,
|
||
|
|
"quantization_config": {
|
||
|
|
"config_groups": {
|
||
|
|
"group_0": {
|
||
|
|
"input_activations": {
|
||
|
|
"block_structure": null,
|
||
|
|
"dynamic": true,
|
||
|
|
"group_size": null,
|
||
|
|
"num_bits": 8,
|
||
|
|
"observer": "memoryless",
|
||
|
|
"observer_kwargs": {},
|
||
|
|
"strategy": "token",
|
||
|
|
"symmetric": true,
|
||
|
|
"type": "int"
|
||
|
|
},
|
||
|
|
"output_activations": null,
|
||
|
|
"targets": [
|
||
|
|
"Linear"
|
||
|
|
],
|
||
|
|
"weights": {
|
||
|
|
"block_structure": null,
|
||
|
|
"dynamic": false,
|
||
|
|
"group_size": null,
|
||
|
|
"num_bits": 8,
|
||
|
|
"observer": "minmax",
|
||
|
|
"observer_kwargs": {},
|
||
|
|
"strategy": "channel",
|
||
|
|
"symmetric": true,
|
||
|
|
"type": "int"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"format": "int-quantized",
|
||
|
|
"global_compression_ratio": 1.0,
|
||
|
|
"ignore": [
|
||
|
|
"re:.*linear_attn.*",
|
||
|
|
"re:.*self_attn.*",
|
||
|
|
"re:.*shared_expert.*",
|
||
|
|
"re:.*linear_attn.in_proj_ba.*",
|
||
|
|
"re:.*conv1d.*",
|
||
|
|
"re:.*A_log.*",
|
||
|
|
"re:.*shared_expert_gate.*",
|
||
|
|
"re:.*bias.*",
|
||
|
|
"re:.*norm.*",
|
||
|
|
"re:.*mlp.gate.*",
|
||
|
|
"re:.*embed_tokens.*",
|
||
|
|
"re:.*lm_head.*",
|
||
|
|
"re:.*mtp.*"
|
||
|
|
],
|
||
|
|
"kv_cache_scheme": null,
|
||
|
|
"quant_method": "compressed-tensors",
|
||
|
|
"quantization_status": "frozen"
|
||
|
|
}
|
||
|
|
}
|