gemmagain-trained-s1 / config.json
ToastyPigeon's picture
Update config.json
cc5057b verified
{
"_sliding_window_pattern": 6,
"architectures": [
"GemmagainForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"auto_map": {
"AutoConfig": "configuration_gemmagain.GemmagainConfig",
"AutoModelForCausalLM": "modeling_gemmagain.GemmagainForCausalLM"
},
"bos_token_id": 2,
"cache_implementation": "hybrid",
"dtype": "float32",
"eos_token_id": 1,
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 10240,
"layer_sequence": [
0,
1,
1,
2,
3,
3,
4,
5,
5,
[
6,
18
],
[
18,
21,
3
],
[
21,
34
]
],
"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",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"full_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention",
"sliding_attention"
],
"max_position_embeddings": 131072,
"model_type": "gemma3",
"num_attention_heads": 8,
"num_hidden_layers": 34,
"num_key_value_heads": 4,
"pad_token_id": 0,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_local_base_freq": 10000.0,
"rope_scaling": {
"factor": 8.0,
"rope_type": "linear"
},
"rope_theta": 1000000.0,
"sliding_window": 1024,
"sliding_window_pattern": 6,
"transformers_version": "4.57.1",
"use_bidirectional_attention": false,
"use_cache": false,
"vocab_size": 262208
}