fredrunit's picture
EmbeddingGemma 2 text-only 8-bit MLX (from google/embeddinggemma-2 914f7f89)
997ec04 verified
Raw History Blame Contribute Delete
2.25 kB
{
"architectures": [
"EmbeddingGemma2Model"
],
"dtype": "bfloat16",
"initializer_range": 0.02,
"model_type": "embedding_gemma2",
"quantization": {
"bits": 8,
"group_size": 64,
"mode": "affine"
},
"quantization_config": {
"bits": 8,
"group_size": 64,
"mode": "affine"
},
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"dtype": "bfloat16",
"embedding_dim": 768,
"eos_token_id": 1,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 512,
"hidden_size_per_layer_input": 512,
"initializer_range": 0.02,
"intermediate_size": 2048,
"layer_types": [
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention"
],
"max_position_embeddings": 262144,
"model_type": "embedding_gemma2_text",
"num_attention_heads": 4,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"pad_token_id": 0,
"per_layer_config": {
"05": {
"head_dim": 512,
"num_key_value_heads": 1
},
"11": {
"head_dim": 512,
"num_key_value_heads": 1
},
"17": {
"head_dim": 512,
"num_key_value_heads": 1
},
"23": {
"head_dim": 512,
"num_key_value_heads": 1
}
},
"rms_norm_eps": 1e-06,
"rope_parameters": {
"full_attention": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_attention": {
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"sliding_window": 512,
"vocab_size": 262144
},
"transformers_version": "5.18.0.dev0"
}