farbodtavakkoli's picture
Copy of farbodtavakkoli/OTel-LLM-8.3B-Classification at ee00910
d0d5b0e verified
Raw History Blame Contribute Delete
3.1 kB
{
"_sliding_window_pattern": 1,
"architectures": [
"Gemma3TextForSequenceClassification"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"bos_token_id": 2,
"cache_implementation": "hybrid",
"dtype": "bfloat16",
"eos_token_id": 1,
"final_logit_softcapping": 30.0,
"head_dim": 128,
"hidden_act": "gelu_pytorch_tanh",
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 4096,
"id2label": {
"0": "C1",
"1": "C2",
"2": "C3",
"3": "C4",
"4": "C5",
"5": "C6",
"6": "C7",
"7": "C8"
},
"initializer_range": 0.02,
"intermediate_size": 16384,
"label2id": {
"C1": 0,
"C2": 1,
"C3": 2,
"C4": 3,
"C5": 4,
"C6": 5,
"C7": 6,
"C8": 7
},
"layer_type": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"model_type": "gemma3_text",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 128001,
"query_pre_attn_scalar": 128,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"full_attention": {
"attn_factor": 1.0,
"beta_fast": 64.0,
"beta_slow": 1.0,
"extrapolation_factor": 1.0,
"factor": 4.0,
"original_max_position_embeddings": 8192,
"rope_theta": 10000,
"rope_type": "yarn"
},
"rope_theta": null,
"rope_type": "default",
"sliding_attention": {
"rope_theta": 10000,
"rope_type": "default"
}
},
"sliding_window": 32768,
"sliding_window_pattern": 1,
"tie_word_embeddings": true,
"transformers_version": "5.2.0",
"use_bidirectional_attention": false,
"use_cache": false,
"vocab_size": 128256
}