|
{ |
|
"architectures": [ |
|
"Qwen2TSForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"auto_map": { |
|
"AutoConfig": "configuration_qwen2.Qwen2TSConfig", |
|
"AutoModel": "modeling_qwen2.Qwen2TSForCausalLM", |
|
"AutoModelForCausalLM": "modeling_qwen2.Qwen2TSForCausalLM", |
|
"AutoProcessor": "processing_qwen2_ts.Qwen2TSProcessor" |
|
}, |
|
"bos_token_id": 151643, |
|
"eos_token_id": 151645, |
|
"hidden_act": "silu", |
|
"hidden_size": 5120, |
|
"ignore_index": -100, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 13824, |
|
"max_position_embeddings": 32768, |
|
"max_window_layers": 70, |
|
"model_type": "qwen2", |
|
"num_attention_heads": 40, |
|
"num_hidden_layers": 48, |
|
"num_key_value_heads": 8, |
|
"pad_token_id": 151643, |
|
"quantization_config": { |
|
"config_groups": { |
|
"group_0": { |
|
"input_activations": null, |
|
"output_activations": null, |
|
"targets": [ |
|
"Linear" |
|
], |
|
"weights": { |
|
"actorder": null, |
|
"block_structure": null, |
|
"dynamic": false, |
|
"group_size": 128, |
|
"num_bits": 4, |
|
"observer": "minmax", |
|
"observer_kwargs": {}, |
|
"strategy": "group", |
|
"symmetric": true, |
|
"type": "int" |
|
} |
|
} |
|
}, |
|
"format": "pack-quantized", |
|
"global_compression_ratio": null, |
|
"ignore": [ |
|
"lm_head", |
|
"ts_encoder.mlp.0", |
|
"ts_encoder.mlp.2", |
|
"ts_encoder.mlp.4", |
|
"ts_encoder.mlp.6", |
|
"ts_encoder.mlp.8" |
|
], |
|
"kv_cache_scheme": null, |
|
"quant_method": "compressed-tensors", |
|
"quantization_status": "compressed" |
|
}, |
|
"rms_norm_eps": 1e-06, |
|
"rope_theta": 1000000.0, |
|
"sliding_window": 131072, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.52.4", |
|
"ts": { |
|
"hidden_size": 5120, |
|
"max_length": 2048, |
|
"num_features": 2, |
|
"num_layers": 5, |
|
"patch_size": 16 |
|
}, |
|
"ts_token_end_index": 151666, |
|
"ts_token_start_index": 151665, |
|
"use_cache": false, |
|
"use_sliding_window": false, |
|
"vocab_size": 152064 |
|
} |