mgoin's picture
Updated compression_config to quantization_config
e9ee95a verified
{
"_name_or_path": "/home/rshaw/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/e1945c40cd546c78e41f1151f4db032b271faeaa",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128009,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.42.4",
"use_cache": true,
"vocab_size": 128256,
"quantization_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": [
"re:.*self_attn*"
],
"weights": {
"block_structure": null,
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "minmax",
"observer_kwargs": {},
"strategy": "channel",
"symmetric": true,
"type": "int"
}
},
"group_1": {
"input_activations": {
"block_structure": null,
"dynamic": true,
"group_size": null,
"num_bits": 8,
"observer": "memoryless",
"observer_kwargs": {},
"strategy": "tensor",
"symmetric": true,
"type": "float"
},
"output_activations": null,
"targets": [
"re:.*mlp*"
],
"weights": {
"block_structure": null,
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "minmax",
"observer_kwargs": {},
"strategy": "tensor",
"symmetric": true,
"type": "float"
}
}
},
"format": "naive-quantized",
"global_compression_ratio": 1.2282555056239162,
"ignore": [
"model.layers.30.self_attn.q_proj",
"model.layers.30.self_attn.k_proj",
"model.layers.30.self_attn.v_proj",
"model.layers.30.self_attn.o_proj",
"model.layers.30.mlp.gate_proj",
"model.layers.30.mlp.up_proj",
"model.layers.30.mlp.down_proj",
"model.layers.31.self_attn.q_proj",
"model.layers.31.self_attn.k_proj",
"model.layers.31.self_attn.v_proj",
"model.layers.31.self_attn.o_proj",
"model.layers.31.mlp.gate_proj",
"model.layers.31.mlp.up_proj",
"model.layers.31.mlp.down_proj",
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "frozen"
}
}