initial upload into repo

config.json

@@ -0,0 +1,90 @@
+{
+  "model_name": "bling-cerebras-1.3b-0.1",
+  "description": "Instruct train fine-tuning using distilled knowledge based critical reading tasks training dataset",
+  "training_timestamp": "Sat Oct 7 08:52:05 2023",
+  "training_comments": "cerebras-1.3b-base",
+  "_name_or_path": "cerebras/Cerebras-GPT-1.3B",
+  "model_type": "gpt2",
+  "vocab_size": 50257,
+  "n_positions": 2048,
+  "n_embd": 2048,
+  "n_layer": 24,
+  "n_head": 16,
+  "n_inner": 8192,
+  "activation_function": "gelu",
+  "resid_pdrop": 0.0,
+  "embd_pdrop": 0.0,
+  "attn_pdrop": 0.0,
+  "layer_norm_epsilon": 1e-05,
+  "initializer_range": 0.02,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "scale_attn_weights": true,
+  "use_cache": true,
+  "scale_attn_by_inverse_layer_idx": false,
+  "reorder_and_upcast_attn": false,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "return_dict": true,
+  "output_hidden_states": false,
+  "output_attentions": false,
+  "torchscript": false,
+  "torch_dtype": null,
+  "use_bfloat16": false,
+  "tf_legacy_loss": false,
+  "pruned_heads": {},
+  "tie_word_embeddings": true,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "chunk_size_feed_forward": 0,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": null,
+  "architectures": null,
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "tokenizer_class": null,
+  "prefix": null,
+  "pad_token_id": null,
+  "sep_token_id": null,
+  "decoder_start_token_id": null,
+  "task_specific_params": null,
+  "problem_type": null,
+  "transformers_version": "4.28.1",
+  "trained": "custom training"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18fc7e86391e3d51531015f317f9c62bbddd477b2f2b8b53ef3839433e51e3da
+size 5363683717