72 lines
1.7 KiB
JSON
72 lines
1.7 KiB
JSON
{
|
|
"architectures": [
|
|
"Qwen3ForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 151643,
|
|
"eos_token_id": 151645,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 5120,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 25600,
|
|
"max_position_embeddings": 40960,
|
|
"max_window_layers": 64,
|
|
"model_type": "qwen3",
|
|
"num_attention_heads": 64,
|
|
"num_hidden_layers": 64,
|
|
"num_key_value_heads": 8,
|
|
"quantization_config": {
|
|
"config_groups": {
|
|
"group_0": {
|
|
"input_activations": {
|
|
"actorder": null,
|
|
"block_structure": null,
|
|
"dynamic": true,
|
|
"group_size": null,
|
|
"num_bits": 8,
|
|
"observer": null,
|
|
"observer_kwargs": {},
|
|
"strategy": "token",
|
|
"symmetric": true,
|
|
"type": "int"
|
|
},
|
|
"output_activations": null,
|
|
"targets": [
|
|
"Linear"
|
|
],
|
|
"weights": {
|
|
"actorder": null,
|
|
"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": null,
|
|
"ignore": [
|
|
"lm_head"
|
|
],
|
|
"kv_cache_scheme": null,
|
|
"quant_method": "compressed-tensors",
|
|
"quantization_status": "compressed"
|
|
},
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 1000000,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.51.3",
|
|
"use_cache": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 151936
|
|
} |