初始化项目，由ModelHub XC社区提供模型

Model: Deeokay/GPT2-medium-custom-v1.0
Source: Original Platform

.gitattributes

@@ -0,0 +1,38 @@
+*.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
+gpt2-medium-custom-v1.0_bf32.gguf filter=lfs diff=lfs merge=lfs -text
+gpt2-medium-custom-v1.0_f16.gguf filter=lfs diff=lfs merge=lfs -text
+gpt2-medium-custom-v1.0_Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,241 @@
+---
+library_name: transformers
+tags: []
+---
+
+# SUMMARY
+
+Just a model using to learn Fine Tuning of 'gpt2-medium'
+- on a self made datasets
+- on a self made special tokens
+- on a multiple fine tuned with ~15K dataset (in progress mode)
+
+If interested in how I got to this point and how I created the datasets you can visit:  
+[Crafting GPT2 for Personalized AI-Preparing Data the Long Way](https://medium.com/@deeokay/the-soul-in-the-machine-crafting-gpt2-for-personalized-ai-9d38be3f635f)
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+# FINE TUNED - BASE MODEL
+I would consider this [GPT2-medium-custom-v1.0](https://huggingface.co/Deeokay/GPT2-medium-custom-v1.0) a the base model to start my Fine Tuning 2.0 on specific Datasets. 
+- Previous models of this: gpt-special-tokens-medium(1~4) are consider beta check-points to this
+
+This model is available to test on Ollama [Deeokay/mediumgpt2](https://ollama.com/deeokay/mediumgpt2) it is not perfect and I am still working out some stuff, but I am quite proud that I was able to make it this far.
+Please note, the acutal GGUF file is also included in this repository if you would like to create your own versions (templates etc.)
+
+
+## DECLARING NEW SPECIAL TOKENS 
+
+```python
+special_tokens_dict = {
+    'eos_token': '<|STOP|>',
+    'bos_token': '<|STOP|>',
+    'pad_token': '<|PAD|>',
+    'additional_special_tokens': ['<|BEGIN_QUERY|>', '<|BEGIN_QUERY|>', 
+                                  '<|BEGIN_ANALYSIS|>', '<|END_ANALYSIS|>',
+                                  '<|BEGIN_RESPONSE|>', '<|END_RESPONSE|>',
+                                  '<|BEGIN_SENTIMENT|>', '<|END_SENTIMENT|>',
+                                  '<|BEGIN_CLASSIFICATION|>', '<|END_CLASSIFICATION|>',]
+}
+
+tokenizer.add_special_tokens(special_tokens_dict)
+model.resize_token_embeddings(len(tokenizer))
+
+tokenizer.eos_token_id = tokenizer.convert_tokens_to_ids('<|STOP|>')
+tokenizer.bos_token_id = tokenizer.convert_tokens_to_ids('<|STOP|>')
+tokenizer.pad_token_id = tokenizer.convert_tokens_to_ids('<|PAD|>')
+```
+
+The order of tokens is as follows: 
+
+```python
+def combine_text(user_prompt, analysis, sentiment, new_response, classification):    
+    user_q = f"<|STOP|><|BEGIN_QUERY|>{user_prompt}<|END_QUERY|>"
+    analysis = f"<|BEGIN_ANALYSIS|>{analysis}<|END_ANALYSIS|>"
+    new_response = f"<|BEGIN_RESPONSE|>{new_response}<|END_RESPONSE|>"
+    classification = f"<|BEGIN_CLASSIFICATION|>{classification}<|END_CLASSIFICATION|>"
+    sentiment = f"<|BEGIN_SENTIMENT|>Sentiment: {sentiment}<|END_SENTIMENT|><|STOP|>"
+    return user_q + analysis + new_response + classification + sentiment
+```
+
+## INFERANCING 
+
+I am currently testing two ways, if anyone knows a better one, please let me know! 
+
+```python
+import torch
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+models_folder = "Deeokay/gpt2-medium-custom-v1.0"
+
+model = GPT2LMHeadModel.from_pretrained(models_folder)
+tokenizer = GPT2Tokenizer.from_pretrained(models_folder)
+
+# Device configuration <<change as needed>> 
+device = torch.device("cpu")
+model.to(device)
+
+```
+
+### OPTION 1 INFERFENCE
+
+```python
+import time
+
+class Stopwatch:
+    def __init__(self):
+        self.start_time = None
+        self.end_time = None
+
+    def start(self):
+        self.start_time = time.time()
+
+    def stop(self):
+        self.end_time = time.time()
+
+    def elapsed_time(self):
+        if self.start_time is None:
+            return "Stopwatch hasn't been started"
+        if self.end_time is None:
+            return "Stopwatch hasn't been stopped"
+        return self.end_time - self.start_time
+
+stopwatch1 = Stopwatch()
+
+def generate_response(input_text, max_length=250):
+    
+	stopwatch1.start()
+    
+	# Prepare the input
+	# input_text = f"<|BEGIN_QUERY|>{input_text}<|END_QUERY|><|BEGIN_ANALYSIS|>{input_text}<|END_ANALYSIS|><|BEGIN_RESPONSE|>"
+	input_text = f"<|BEGIN_QUERY|>{input_text}<|END_QUERY|><|BEGIN_ANALYSIS|>"
+    
+	input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)
+
+	# Create attention mask
+	attention_mask = torch.ones_like(input_ids).to(device)
+    
+	# Generate
+	output = model.generate(
+    	input_ids,
+    	max_new_tokens=max_length,
+    	num_return_sequences=1,
+    	no_repeat_ngram_size=2,
+    	attention_mask=attention_mask,
+    	pad_token_id=tokenizer.eos_token_id,
+    	eos_token_id=tokenizer.convert_tokens_to_ids('<|STOP|>'),
+	)
+    
+	stopwatch1.stop()
+    
+	return tokenizer.decode(output[0], skip_special_tokens=False)
+```
+
+### OPTION 2 INFERNCE
+
+```python
+import time
+
+class Stopwatch:
+    def __init__(self):
+        self.start_time = None
+        self.end_time = None
+
+    def start(self):
+        self.start_time = time.time()
+
+    def stop(self):
+        self.end_time = time.time()
+
+    def elapsed_time(self):
+        if self.start_time is None:
+            return "Stopwatch hasn't been started"
+        if self.end_time is None:
+            return "Stopwatch hasn't been stopped"
+        return self.end_time - self.start_time
+
+stopwatch2 = Stopwatch()
+
+def generate_response2(input_text, max_length=250):
+    
+	stopwatch2.start()
+    
+	# Prepare the input
+	# input_text = f"<|BEGIN_QUERY|>{input_text}<|END_QUERY|><|BEGIN_ANALYSIS|>{input_text}<|END_ANALYSIS|><|BEGIN_RESPONSE|>"
+	input_text = f"<|BEGIN_QUERY|>{input_text}<|END_QUERY|><|BEGIN_ANALYSIS|>"
+	input_ids = tokenizer.encode(input_text, return_tensors="pt").to(device)
+
+	# Create attention mask
+	attention_mask = torch.ones_like(input_ids).to(device)
+
+	# # 2ND OPTION FOR : Generate
+	output = model.generate(
+    	input_ids,
+    	max_new_tokens=max_length,
+    	attention_mask=attention_mask,
+    	do_sample=True,
+    	temperature=0.4, # this can be played around 
+    	top_k=60,        # this can be played around 
+    	no_repeat_ngram_size=2,
+    	pad_token_id=tokenizer.pad_token_id,
+    	eos_token_id=tokenizer.eos_token_id,
+	)
+    
+	stopwatch2.stop()
+	return tokenizer.decode(output[0], skip_special_tokens=False)
+```
+### DECODING ANSWER
+
+When I need just the response
+
+```python
+def decode(text):
+	full_text = text
+    
+	# Extract the response part
+	start_token = "<|BEGIN_RESPONSE|>"
+	end_token = "<|END_RESPONSE|>"
+	start_idx = full_text.find(start_token)
+	end_idx = full_text.find(end_token)
+    
+	if start_idx != -1 and end_idx != -1:
+    	response = full_text[start_idx + len(start_token):end_idx].strip()
+	else:
+    	response = full_text.strip()
+    
+	return response
+```
+
+### MY SETUP
+
+I use the stopwatch to time the responses and I use both inference to see the difference 
+
+```python
+input_text = "Who is Steve Jobs and what was contribution?"
+response1_full = generate_response(input_text)
+#response1 = decode(response1_full)
+print(f"Input: {input_text}")
+print("=======================================")
+print(f"Response1: {response1_full}")
+elapsed1 = stopwatch1.elapsed_time()
+print(f"Process took {elapsed1:.4f} seconds")
+print("=======================================")
+response2_full = generate_response2(input_text)
+#response2 = decode(response2_full)
+print(f"Response2: {response2_full}")
+elapsed2 = stopwatch2.elapsed_time()
+print(f"Process took {elapsed2:.4f} seconds")
+print("=======================================")
+```
+
+
+### Out-of-Scope Use
+
+Well everything that has a factual data.. trust at your own risk! 
+
+Never tested on mathamatical knowledge. 
+
+I quite enjoy how the response feels closer to what I had in mind.. 
+
+
+

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|BEGIN_ANALYSIS|>": 50260,
+  "<|BEGIN_CLASSIFICATION|>": 50266,
+  "<|BEGIN_QUERY|>": 50259,
+  "<|BEGIN_RESPONSE|>": 50262,
+  "<|BEGIN_SENTIMENT|>": 50264,
+  "<|END_ANALYSIS|>": 50261,
+  "<|END_CLASSIFICATION|>": 50267,
+  "<|END_RESPONSE|>": 50263,
+  "<|END_SENTIMENT|>": 50265,
+  "<|PAD|>": 50258,
+  "<|STOP|>": 50257
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "/Users/deeokay/Documents/LLMs/GPT2/hf_models/GPT2-medium-v1.2",
+  "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": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "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": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 50268
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.41.0"
+}

gpt2-medium-custom-v1.0_Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5aebd5bf5e54a76d04a263025b2452383e6c5157af20d681713a5e0b5cf334
+size 437511616

gpt2-medium-custom-v1.0_bf32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54849e8212984113c2a5811a40750859acdfb7372829f9fabb81fd70fb6b5f77
+size 1627019200

gpt2-medium-custom-v1.0_f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2772c9523e44a7d5b2e309278e1707e4c3bdc3bc8bce811d6d7c94e4878ca373
+size 817141696

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2337475b5d9d2dc627ce2e5cff2b4710318807f9e43ea6783bd0599eb12cdff
+size 1419367936

special_tokens_map.json

@@ -0,0 +1,42 @@
+{
+  "additional_special_tokens": [
+    "<|BEGIN_QUERY|>",
+    "<|BEGIN_QUERY|>",
+    "<|BEGIN_ANALYSIS|>",
+    "<|END_ANALYSIS|>",
+    "<|BEGIN_RESPONSE|>",
+    "<|END_RESPONSE|>",
+    "<|BEGIN_SENTIMENT|>",
+    "<|END_SENTIMENT|>",
+    "<|BEGIN_CLASSIFICATION|>",
+    "<|END_CLASSIFICATION|>"
+  ],
+  "bos_token": {
+    "content": "<|STOP|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|STOP|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,122 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|STOP|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|PAD|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50259": {
+      "content": "<|BEGIN_QUERY|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50260": {
+      "content": "<|BEGIN_ANALYSIS|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50261": {
+      "content": "<|END_ANALYSIS|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50262": {
+      "content": "<|BEGIN_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50263": {
+      "content": "<|END_RESPONSE|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<|BEGIN_SENTIMENT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "<|END_SENTIMENT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50266": {
+      "content": "<|BEGIN_CLASSIFICATION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50267": {
+      "content": "<|END_CLASSIFICATION|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|BEGIN_QUERY|>",
+    "<|BEGIN_QUERY|>",
+    "<|BEGIN_ANALYSIS|>",
+    "<|END_ANALYSIS|>",
+    "<|BEGIN_RESPONSE|>",
+    "<|END_RESPONSE|>",
+    "<|BEGIN_SENTIMENT|>",
+    "<|END_SENTIMENT|>",
+    "<|BEGIN_CLASSIFICATION|>",
+    "<|END_CLASSIFICATION|>"
+  ],
+  "bos_token": "<|STOP|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|STOP|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "<|PAD|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}