First release

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "EleutherAI/pythia-70m",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "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
+}

evaluation/all_results.json

@@ -0,0 +1,5 @@
+{
+    "predict_runtime": 262.3617,
+    "predict_samples_per_second": 3.903,
+    "predict_steps_per_second": 0.976
+}

evaluation/metrics.json

@@ -0,0 +1 @@
+{"run_name": "/70m-Pythia/Loquace-70m/evaluation", "predict_runtime": 262.3617, "predict_samples_per_second": 3.903, "predict_steps_per_second": 0.976}

evaluation/predict_results.json

@@ -0,0 +1,5 @@
+{
+    "predict_runtime": 262.3617,
+    "predict_samples_per_second": 3.903,
+    "predict_steps_per_second": 0.976
+}

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 sha256:42847a7803a82d1278597b7fccb2bee36c9d8511031f12e8ba3e8bc70ee23845
+size 166050443

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|>"
+}