|
{ |
|
"_name_or_path": "/network/sadkins/llama7b_sparse_24_w4a16_group128", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"compression_config": { |
|
"config_groups": { |
|
"group_0": { |
|
"input_activations": null, |
|
"output_activations": null, |
|
"targets": [ |
|
"Linear" |
|
], |
|
"weights": { |
|
"block_structure": null, |
|
"dynamic": false, |
|
"group_size": 128, |
|
"num_bits": 4, |
|
"observer": "minmax", |
|
"observer_kwargs": {}, |
|
"strategy": "group", |
|
"symmetric": true, |
|
"type": "int" |
|
} |
|
} |
|
}, |
|
"format": "marlin-24", |
|
"global_compression_ratio": 1.896287597650382, |
|
"ignore": [ |
|
"lm_head" |
|
], |
|
"quant_method": "compressed-tensors", |
|
"quantization_status": "frozen", |
|
"sparsity_config": { |
|
"format": "dense", |
|
"global_sparsity": 50.79734011764465, |
|
"registry_requires_subclass": false, |
|
"sparsity_structure": "2:4" |
|
} |
|
}, |
|
"eos_token_id": 2, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 11008, |
|
"max_position_embeddings": 4096, |
|
"model_type": "llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 32, |
|
"pretraining_tp": 1, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 10000.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.40.0", |
|
"use_cache": true, |
|
"vocab_size": 32000 |
|
} |