|
{ |
|
"_name_or_path": "alpindale/Meta-Llama-3.1-8B-Instruct-W8A8-INT8-Dynamic-Per-Token", |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 128000, |
|
"eos_token_id": [ |
|
128001, |
|
128008, |
|
128009 |
|
], |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 4096, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 14336, |
|
"max_position_embeddings": 131072, |
|
"mlp_bias": false, |
|
"model_type": "llama", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 8, |
|
"pretraining_tp": 1, |
|
"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": 1.458959021545191, |
|
"ignore": [ |
|
"lm_head" |
|
], |
|
"kv_cache_scheme": null, |
|
"quant_method": "compressed-tensors", |
|
"quantization_status": "compressed" |
|
}, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": { |
|
"factor": 8.0, |
|
"high_freq_factor": 4.0, |
|
"low_freq_factor": 1.0, |
|
"original_max_position_embeddings": 8192, |
|
"rope_type": "llama3" |
|
}, |
|
"rope_theta": 500000.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.47.1", |
|
"use_cache": true, |
|
"vocab_size": 128256 |
|
} |
|
|