Uploading Maestro-TSD-bpe20k

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "runs/gen_Maestro_TSD/TSD_bpe20000",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 2,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 3,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "pad": 0,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 20000
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "epsilon_cutoff": null,
+  "eta_cutoff": null,
+  "max_length": null,
+  "max_new_tokens": 512,
+  "pad_token_id": 0,
+  "temperature": 2.5,
+  "top_k": 15,
+  "top_p": 0.95,
+  "transformers_version": "4.33.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d520e24e5c30ef2d6823aa00e8aa8f2c81f97d4654d1d41ec2281568b75e17b2
+size 196487704