Upload model

config.json

@@ -1,32 +1,45 @@
-{
-  "_name_or_path": "zynxware/nexus-prime",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
-  "model_type": "gpt2",
-  "tokenizer_type": "GPT2Tokenizer",
-  "vocab_size": 50257,
-  "n_positions": 1024,
-  "n_embd": 768,
-  "n_layer": 6,
-  "n_head": 12,
-  "n_inner": 3072,
-  "activation_function": "gelu_new",
-  "resid_pdrop": 0.1,
-  "embd_pdrop": 0.1,
-  "attn_pdrop": 0.1,
-  "layer_norm_epsilon": 1e-05,
-  "initializer_range": 0.02,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "summary_activation": null,
-  "summary_proj_to_labels": true,
-  "summary_first_dropout": 0.1,
-  "torch_dtype": "float16",
-  "transformers_version": "4.21.0",
-  "transformers_info": {
-    "auto_mapping": null,
-    "custom_classes": null,
-    "exported_with": "4.21.0"
-  }
-}
+{
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -1,31 +1,6 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
-  "pad_token_id": 50256,
-  "transformers_version": "4.21.0",
-  "max_length": 1000,
-  "min_length": 1,
-  "do_sample": true,
-  "early_stopping": false,
-  "num_beams": 1,
-  "temperature": 0.7,
-  "top_k": 50,
-  "top_p": 0.9,
-  "repetition_penalty": 1.2,
-  "length_penalty": 1.0,
-  "no_repeat_ngram_size": 3,
-  "bad_words_ids": null,
-  "force_words_ids": null,
-  "encoder_no_repeat_ngram_size": 0,
-  "decoder_start_token_id": null,
-  "num_return_sequences": 1,
-  "diversity_penalty": 0.0,
-  "remove_invalid_values": true,
-  "exponential_decay_length_penalty": null,
-  "suppress_tokens": null,
-  "begin_suppress_tokens": null,
-  "forced_bos_token_id": null,
-  "forced_eos_token_id": null,
-  "max_new_tokens": 80
-}
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.56.2"
+}