Upload FlaxT5ForConditionalGeneration

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "yhavinga/ul2-large-translate-en-nl_ckpt_3440000",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "silu",
+  "dropout_rate": 0.01,
+  "early_stopping": true,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-silu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "max_length": 370,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_beams": 4,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "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": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "eos_token_id": 1,
+  "max_length": 370,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc04ddb46af02f81a9f6363c9b63b13310303ee9495bc1d6c2e6c6588697c7d
+size 1632415968