初始化项目，由ModelHub XC社区提供模型

Model: rahul77/gpt-2-finetune
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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 +1,82 @@
+---
+license: apache-2.0
+datasets:
+- rahul77/rahul-gpt2-1k
+language:
+- en
+base_model: openai-community/gpt2
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- text-generation
+- GPT-2
+- fine-tuned
+- language-model
+- transformers
+---
+
+# GPT-2 Fine-Tuned Model
+
+This is a fine-tuned version of the GPT-2 model designed for text generation tasks. The model has been fine-tuned to improve its performance on generating coherent and contextually relevant text.
+
+## Model Details
+
+- **Model Name:** GPT-2 Fine-Tuned
+- **Base Model:** gpt2
+- **Architecture:** GPT2LMHeadModel
+- **Tokenization:** Supported
+  - `pad_token_id`: 50256
+  - `bos_token_id`: 50256
+  - `eos_token_id`: 50256
+
+## Supported Tasks
+
+This model supports the following task:
+
+- **Text Generation**
+
+## Configuration
+
+### Model Configuration (config.json)
+
+- **Hidden Size:** 768
+- **Number of Layers:** 12
+- **Number of Attention Heads:** 12
+- **Vocab Size:** 50257
+- **Token Type IDs:** Not used
+
+### Generation Configuration (generation_config.json)
+
+- **Sampling Temperature:** 0.7
+- **Top-p (nucleus sampling):** 0.9
+- **Pad Token ID:** 50256
+- **Bos Token ID:** 50256
+- **Eos Token ID:** 50256
+
+## Usage
+
+To use this model for text generation via the Hugging Face API, use the following Python code snippet:
+
+```python
+import requests
+
+api_url = "https://api-inference.huggingface.co/models/rahul77/gpt-2-finetune"
+headers = {
+    "Authorization": "Bearer YOUR_API_TOKEN",  # Replace with your Hugging Face API token
+    "Content-Type": "application/json"
+}
+
+data = {
+    "inputs": "What is a large language model?",
+    "parameters": {
+        "max_length": 50
+    }
+}
+
+response = requests.post(api_url, headers=headers, json=data)
+
+if response.status_code == 200:
+    print(response.json())
+else:
+    print(f"Error: {response.status_code}")
+    print(response.json())

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": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.31.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e596c6e7c4d8cbb37d7116caab786ae303eaef6450523a28676547f5a247af
+size 248928026

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_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": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}