khazri-2 / config.json
Yusiko's picture
Upload 9 files
b399ea6 verified
Raw
History Blame Contribute Delete
1.26 kB
{
"activation_function": "gelu_new",
"add_cross_attention": false,
"architectures": [
"SynapseGPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 2,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 22,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 512,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 32,
"n_positions": 512,
"pad_token_id": 1,
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"tie_word_embeddings": true,
"transformers_version": "5.10.1",
"use_cache": false,
"vocab_size": 32000,
"auto_map": {
"AutoModelForCausalLM": "modeling_synapse.SynapseGPT2LMHeadModel"
},
"synapse": {
"version": "v4_from_scratch",
"requires_controller_for_best_results": true,
"routes": [
"NSR_CALCULATOR",
"UQM_ABSTAIN",
"TMS_CONTEXT",
"MODEL_FALLBACK"
],
"pure_model_note": "Use generate() for pure model; use synapse_generate() for controlled inference."
}
}