Make model load with `T5EncoderModel.from_pretrained()` (#5)

- d53fec309ea2cd610d031565454df58818d56e9943eef3ea4e3da08bbc9719d8 (2a69a0fb61cd3bcc0fb21015ad0e1e0aad42af44)
- b01b86f55688850c615c23cfe95c5c1d089b7bb7ba891d180c84d26646f752f0 (926976a6d23fef099b1f11f41db7ebe0dc702e1f)
- b0ba4f0eba680f009b8720b25f99776ed0d72e5635499f9b4dd2548c73a4375a (91e4c0f88e4253d601f5bed00311a58f1210147b)


Co-authored-by: neggles <[email protected]>

.gitattributes

@@ -8,3 +8,4 @@
 *.onnx filter=lfs diff=lfs merge=lfs -text
 pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text
 t5xxl_fp8_e4m3fn.safetensors filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,17 +1,20 @@
 {
-  "_name_or_path": "/home/patrick/t5/t5-v1_1-xxl",
+  "_name_or_path": "mcmonkey/google_t5-v1_1-xxl_encoderonly",
   "architectures": [
-    "T5ForConditionalGeneration"
+    "T5EncoderModel"
   ],
+  "classifier_dropout": 0.0,
   "d_ff": 10240,
   "d_kv": 64,
   "d_model": 4096,
   "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
   "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "num_decoder_layers": 24,
@@ -19,7 +22,11 @@
   "num_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
   "vocab_size": 32128
 }

pytorch_model.safetensors → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0728b33566ab30a1f1dc6a7a42be63fbeedc94c19ff6917098b2f0bee97711e3
-size 10051033696
+oid sha256:af75f22b86630bc37066533dfa02829c2ed41766fefed6073399a07d96d7daf5
+size 9524648592