Erland's picture
Upload TransformerForCausalLM
2291c6a verified
{
"architectures": [
"TransformerForCausalLM"
],
"attn_impl": "parallel_attn",
"bos_token_id": 1,
"elementwise_affine": true,
"eos_token_id": 2,
"fuse_cross_entropy": true,
"fuse_norm": true,
"fuse_swiglu": true,
"hidden_act": "swish",
"hidden_ratio": 4,
"hidden_size": 2048,
"initializer_range": 0.006,
"intermediate_size": null,
"max_position_embeddings": 8192,
"model_type": "transformer",
"norm_eps": 1e-06,
"num_heads": 32,
"num_hidden_layers": 32,
"num_kv_heads": null,
"pad_token_id": 2,
"qk_norm": false,
"qkv_bias": false,
"quantization_config": {
"modules_to_not_convert": null,
"quant_method": "torchao",
"quant_type": {
"default": {
"_data": {
"act_mapping_type": {
"_data": "ASYMMETRIC",
"_type": "MappingType"
},
"group_size": 128,
"layout": {
"_data": {},
"_type": "PlainLayout",
"_version": 1
},
"mapping_type": {
"_data": "SYMMETRIC",
"_type": "MappingType"
},
"set_inductor_config": true
},
"_type": "Int8DynamicActivationInt4WeightConfig",
"_version": 1
}
},
"quant_type_kwargs": {}
},
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.51.3",
"use_cache": true,
"vocab_size": 32000,
"window_size": null
}