|
{ |
|
"_name_or_path": "/nm/drive0/alexandre/cache/hub/models--Qwen--Qwen2-0.5B-Instruct/snapshots/c291d6fce4804a1d39305f388dd32897d1f7acc4", |
|
"architectures": [ |
|
"Qwen2ForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 151643, |
|
"compression_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": 1.2392250398786397, |
|
"ignore": [ |
|
"lm_head" |
|
], |
|
"kv_cache_scheme": null, |
|
"quant_method": "compressed-tensors", |
|
"quantization_status": "frozen", |
|
"sparsity_config": { |
|
"format": "dense", |
|
"global_sparsity": 1.0414135120688999, |
|
"registry_requires_subclass": false, |
|
"sparsity_structure": "unstructured" |
|
} |
|
}, |
|
"eos_token_id": 151645, |
|
"hidden_act": "silu", |
|
"hidden_size": 896, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 4864, |
|
"max_position_embeddings": 32768, |
|
"max_window_layers": 24, |
|
"model_type": "qwen2", |
|
"num_attention_heads": 14, |
|
"num_hidden_layers": 24, |
|
"num_key_value_heads": 2, |
|
"rms_norm_eps": 1e-06, |
|
"rope_theta": 1000000.0, |
|
"sliding_window": 32768, |
|
"tie_word_embeddings": true, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.42.3", |
|
"use_cache": true, |
|
"use_sliding_window": false, |
|
"vocab_size": 151936 |
|
} |