初始化项目，由ModelHub XC社区提供模型

Model: singtan/my-llm-finetuned-pdf
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 +1,66 @@
+---
+license: apache-2.0
+library_name: transformers
+base_model: gpt2
+tags:
+- text-generation
+- pdf-extraction
+- fine-tuned
+datasets:
+- custom
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# Fine-tuned Language Model (PDF Optimized)
+
+This model is a specialized version of **gpt2**, fine-tuned for high-context coherence based on technical documentation extracted from PDF sources.
+
+## Model Summary
+This model was developed to improve text generation accuracy and contextual understanding for specific domains covered in the provided PDF assets. It leverages the underlying architecture of `gpt2` and is optimized for the structure and vocabulary found in document-based datasets.
+
+### Key Specifications
+| Attribute | Value |
+| :--- | :--- |
+| **Base Architecture** | gpt2 |
+| **Format** | PyTorch (Transformers) |
+| **Task** | Causal Language Modeling |
+| **Language** | English (en) |
+
+## Training Configuration
+The model was fine-tuned using the following high-level hyperparameters to ensure stability and convergence:
+
+- **Epochs:** 3
+- **Batch Size:** 1
+- **Learning Rate:** 5e-05
+- **Optimized for:** Cross-Entropy Loss
+- **Hardware:** cuda
+
+### Performance Metrics
+- **Total Training Loss:** 3.680997848510742
+- **Training Runtime:** 3.6704 seconds
+
+## Data Preprocessing
+The training data was sourced from `dummy.pdf`. The pipeline included:
+1.  **Extraction:** Text recovery using `pypdf`.
+2.  **Normalization:** Regex-based whitespace cleaning and token normalization.
+3.  **Tokenization:** Model-specific subword tokenization with a max sequence length of 512 tokens.
+
+## Usage Instructions
+To utilize this model for inference, use the following snippet:
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+checkpoint = "singtan/my-llm-finetuned-pdf"
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+model = AutoModelForCausalLM.from_pretrained(checkpoint)
+
+prompt = "Insert your context here"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_length=150)
+print(tokenizer.decode(outputs[0]))
+```
+
+## Contact
+Developed by **Bibek** - Senior AI Engineering Portfolio.

config.json

@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "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,
+  "pad_token_id": null,
+  "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
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "5.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde70cc2ec7abb91909f01b41f6870aba7ae6f7c9920ff3f2881f6e23b23a18c
+size 497774208

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}