初始化项目，由ModelHub XC社区提供模型

Model: Sharathhebbar24/math_gpt2
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 +1,53 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- maths
+- arxiv-math
+- gpt2
+- mathgpt2
+datasets:
+- ArtifactAI/arxiv-math-instruct-50k
+widget:
+- text: Which motion is formed by an incident particle?
+  example_title: Example 1
+- text: What type of diffusional modeling is used for diffusion?
+  example_title: Example 2
+
+---
+
+This model is a finetuned version of ```gpt2``` using ```ArtifactAI/arxiv-math-instruct-50k```
+
+## Model description
+
+GPT-2 is a transformers model pre-trained on a very large corpus of English data in a self-supervised fashion. This
+means it was pre-trained on the raw texts only, with no humans labeling them in any way (which is why it can use lots
+of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely,
+it was trained to guess the next word in sentences.
+
+More precisely, inputs are sequences of continuous text of a certain length and the targets are the same sequence,
+shifting one token (word or piece of word) to the right. The model uses a masking mechanism to make sure the
+predictions for the token `i` only use the inputs from `1` to `i` but not the future tokens.
+
+This way, the model learns an inner representation of the English language that can then be used to extract features
+useful for downstream tasks. The model is best at what it was trained for, however, which is generating texts from a
+prompt.
+
+### To use this model
+
+```python
+>>> from transformers import AutoTokenizer, AutoModelForCausalLM
+>>> model_name = "Sharathhebbar24/math_gpt2"
+>>> model = AutoModelForCausalLM.from_pretrained(model_name)
+>>> tokenizer = AutoTokenizer.from_pretrained(model_name)
+>>> def generate_text(prompt):
+>>>  inputs = tokenizer.encode(prompt, return_tensors='pt')
+>>>  outputs = model.generate(inputs, max_length=64, pad_token_id=tokenizer.eos_token_id)
+>>>  generated = tokenizer.decode(outputs[0], skip_special_tokens=True)
+>>>  return generated[:generated.rfind(".")+1]
+>>> prompt = "What structure is classified as a definite lie algebra?"
+>>> res = generate_text(prompt)
+>>> res
+```

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": "4.30.0.dev0",
+  "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": "4.30.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303419557adc384552bf138173829288cd42b52b6a57a1c039cbbe5ae8fd9055
+size 497807706

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|>"
+}