first commit

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/data/public/rw/team-lm/hf_models/gpt_neox_chat_base_20b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_fast",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 44,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.25.1",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50432
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "/data/public/rw/team-lm/hf_models/gpt_neox_chat_base_20b",
+  "special_tokens_map_file": "/root/.cache/huggingface/transformers/d9026dc928c47ac2a72d46fea7db959acc4bacac2176bf32be5c331604b77d32.3ae9ae72462581d20e36bc528e9c47bb30cd671bb21add40ca0b24a0be9fac22",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}