First release

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/pythia-410m/",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

eval/all_results.json

@@ -0,0 +1,5 @@
+{
+    "predict_runtime": 1669.1135,
+    "predict_samples_per_second": 0.613,
+    "predict_steps_per_second": 0.153
+}

eval/metrics.json

@@ -0,0 +1 @@
+{"run_name": ".", "predict_runtime": 1669.1135, "predict_samples_per_second": 0.613, "predict_steps_per_second": 0.153}

eval/predict_results.json

@@ -0,0 +1,5 @@
+{
+    "predict_runtime": 1669.1135,
+    "predict_samples_per_second": 0.613,
+    "predict_steps_per_second": 0.153
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.30.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de00792b5ea756b11704a095e320875ec316527d2102d2ea0d99b4757b150b8
+size 911454333

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}