sharpenb's picture
6daab67d12e9ebf72bab9fcff83bf496fcabbcb539703e9a2ddd065ce132fc95
60a137a verified
raw
history blame
1.45 kB
{
"_attn_implementation_autoset": true,
"_name_or_path": "/tmp/models/tmp65_nd5b7/tmprb3_ze8r",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 1600,
"n_head": 25,
"n_inner": null,
"n_layer": 48,
"n_positions": 1024,
"output_past": true,
"quantization_config": {
"quant_config": {
"offload_meta": false,
"scale_quant_params": null,
"weight_quant_params": {
"axis": 1,
"channel_wise": true,
"group_size": 64,
"nbits": 4,
"optimize": true,
"round_zero": true,
"view_as_float": false
},
"zero_quant_params": null
},
"quant_method": "hqq",
"skip_modules": [
"lm_head"
]
},
"reorder_and_upcast_attn": true,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": true,
"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,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"torch_dtype": "float32",
"transformers_version": "4.48.2",
"use_cache": true,
"vocab_size": 32768
}