Upload 7 files

code/inference.py

@@ -0,0 +1,21 @@
+import os
+import torch
+from transformers import AutoTokenizer, pipeline
+
+GPT_WEIGHTS_NAME = "gpt.pt"
+
+
+def model_fn(model_dir):
+    model = torch.load(os.path.join(model_dir, GPT_WEIGHTS_NAME))
+    tokenizer = AutoTokenizer.from_pretrained(model_dir)
+
+    if torch.cuda.is_available():
+        device = 0
+    else:
+        device = -1
+
+    generation = pipeline(
+        "text-generation", model=model, tokenizer=tokenizer, device=device
+    )
+
+    return generation

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "opt-350m",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": false,
+  "dropout": 0.1,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float16",
+  "transformers_version": "4.20.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

gptj.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d96052c3bc47377d93e0350190b6d057c491d683f515c87c024576b979454990
+size 662549735

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "add_bos_token": true, "special_tokens_map_file": null, "name_or_path": "patrickvonplaten/opt-30b"}