Upload 11 files

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "### End": 50257,
+  "### Instruction:": 50258,
+  "### Response:\n": 50259
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "cerebras/Cerebras-GPT-256m",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 1088,
+  "n_head": 17,
+  "n_inner": 4352,
+  "n_layer": 14,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "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": "bfloat16",
+  "transformers_version": "4.25.1",
+  "use_cache": false,
+  "vocab_size": 50260
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ce70caaa02bb04a31700133532af47e27d9338a05a249964ee7eb38fd447c6
+size 570743021

runs/1680609266.0303035/events.out.tfevents.1680609266.155-248-166-228.146192.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf90f96ffe2a2d08f35ce0f426454b940ce58a4be389e214be793cb569e3a408
+size 5670

runs/events.out.tfevents.1680609266.155-248-166-228.146192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76a41c493aec655cda6f0326a5bb92e15849b0ee637ece2b36632d05f94f5afb
+size 22257

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "### End",
+    "### Instruction:",
+    "### Response:\n"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "cerebras/Cerebras-GPT-256m",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde39b6320c41c89db5700cf1c549c0fa615eb0e4406144aa4e71c417a5d8747
+size 4603