初始化项目，由ModelHub XC社区提供模型

Model: vicgalle/gpt2-open-instruct-v1
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+license: mit
+datasets:
+- hakurei/open-instruct-v1
+language:
+- en
+tags:
+- instruction-tuning
+- gpt2
+- alpaca
+---
+
+# GPT2 finetuned on the open-instruct-v1 dataset
+
+The finetune used the Alpaca format for the prompts, so for better results you have to format the prompt using Alpaca's template. See the following examples below
+
+## Examples
+
+```
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+Pretend you are an alien visiting Earth. Write three opinions you believe.
+
+### Response:
+
+1. Earth is a beautiful place. The sky is clear and the land is lush and diverse.
+2. I believe that there is a species of extraterrestrial life living on the planet. These are known as 'gods' or 'living beings'.
+3. I believe that there is a great conspiracy in place. The government is trying to control the planet and its resources.
+```
+
+
+```
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+Pretend you are an activist against guns. Write three opinions you believe.
+
+### Response:
+
+1. Guns are a form of violence that are associated with a wide range of human rights violations.
+2. Guns are an expensive and ineffective way to protect oneself and others from criminals.
+3. Guns can be used to commit crimes and violence.
+```
+
+
+```
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+Pretend you are a fanatical about guns. Write three opinions you believe.
+
+### Response:
+
+1. Guns are a wonderful weapon. They're incredibly dangerous and can hurt people.
+
+2. Guns are a great way to protect yourself from being shot. They're designed to withstand extreme conditions and fire quickly.
+
+3. Guns are a great way to store and transport large amounts of ammunition. They can be used for everything from self-defense to hunting.
+```

added_tokens.json

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

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "use_cache": false,
+  "vocab_size": 50260
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fdfac1d03291b1af2baff0e8cc143ab0f70d6d09082a9ecbe0233820116cca0
+size 510368814

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67296c9f6df15c6f505ae0a723b462e8791d7bdc68b0aefbca0c2334de7a80da
+size 995623877

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf3f257ed5e349e6fbf9543b28bf4b7a5ba183d1792b53b0bc4b541cc043958
+size 510407229

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f897d747381e914171a9c09f340d8c08e40f692eca00beb4b8be5b487aed8e2
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734de59cf15b5f2a566622381964524a11bcbb41bb635c48b7884155125e8c38
+size 627

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "### End",
+    "### Instruction:",
+    "### Response:\n"
+  ],
+  "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": 1024,
+  "name_or_path": "gpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd426d41f8bd67b57a5cd6badacb225866ccc117f1f6fc559e70d16e0efb4103
+size 3387