mgoin's picture
Updated compression_config to quantization_config
d530a9c verified
{
"_name_or_path": "/network/abhinav/models/gemma-2-2b-it",
"architectures": [
"Gemma2ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": 50.0,
"bos_token_id": 2,
"cache_implementation": "hybrid",
"eos_token_id": [
1,
107
],
"final_logit_softcapping": 30.0,
"head_dim": 256,
"hidden_act": "gelu_pytorch_tanh",
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 2304,
"initializer_range": 0.02,
"intermediate_size": 9216,
"max_position_embeddings": 8192,
"model_type": "gemma2",
"num_attention_heads": 8,
"num_hidden_layers": 26,
"num_key_value_heads": 4,
"pad_token_id": 0,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_theta": 10000.0,
"sliding_window": 4096,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.3",
"use_cache": true,
"vocab_size": 256000,
"quantization_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": "pack-quantized",
"global_compression_ratio": 1.6663703555585414,
"ignore": [
"lm_head"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "frozen",
"sparsity_config": {
"format": "dense",
"global_sparsity": 0.12283362266962997,
"registry_requires_subclass": false,
"sparsity_structure": "unstructured"
}
}
}