初始化项目，由ModelHub XC社区提供模型
Model: QuantaSparkLabs/Mimicer Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -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
|
||||
122
README.md
Normal file
122
README.md
Normal file
@@ -0,0 +1,122 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- assistant
|
||||
- chatbot
|
||||
- distilgpt2
|
||||
- finetuned
|
||||
- experimental
|
||||
- mimicer
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
<div align="center">
|
||||
|
||||
# 🎭 Mimicer
|
||||
|
||||
### *The model that learns to mirror.*
|
||||
|
||||
**For fun!** 🚀
|
||||
|
||||
</div>
|
||||
|
||||
---
|
||||
|
||||
## 🚀 Overview
|
||||
|
||||
Mimicer is an experimental language model fine-tuned to reproduce text patterns and mirror user inputs.
|
||||
|
||||
Unlike traditional assistants optimized for reasoning or instruction following, Mimicer explores identity mapping and response replication through supervised fine-tuning.
|
||||
|
||||
This project serves as a learning platform for model training, dataset design, Hugging Face deployment, and transformer fine-tuning workflows.
|
||||
|
||||
---
|
||||
|
||||
## 📊 Model Details
|
||||
|
||||
| Property | Value |
|
||||
| ---------------- | ------------------------- |
|
||||
| Base Model | DistilGPT2 |
|
||||
| Parameters | 81.9M |
|
||||
| Architecture | GPT-2 Decoder |
|
||||
| Fine-Tuning | Supervised |
|
||||
| Training Samples | 2,500 |
|
||||
| Context Length | 40 Tokens |
|
||||
| Framework | Hugging Face Transformers |
|
||||
| Hardware | NVIDIA T4 |
|
||||
| Repository | QuantaSparkLabs/Mimicer |
|
||||
|
||||
---
|
||||
|
||||
## ⚙️ Training Objective
|
||||
|
||||
Training samples follow a structured format:
|
||||
|
||||
```text
|
||||
Input: Hello world
|
||||
Output: Hello world
|
||||
```
|
||||
|
||||
The objective is to teach the model to reproduce the provided text after the `Output:` prompt.
|
||||
|
||||
Example:
|
||||
|
||||
```text
|
||||
Input: How are you?
|
||||
Output: How are you?
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 💻 Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"QuantaSparkLabs/Mimicer"
|
||||
)
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(
|
||||
"QuantaSparkLabs/Mimicer"
|
||||
)
|
||||
|
||||
prompt = "Input: hello how are you\nOutput:"
|
||||
|
||||
inputs = tokenizer(prompt, return_tensors="pt")
|
||||
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=20,
|
||||
do_sample=False
|
||||
)
|
||||
|
||||
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🔬 Project Goals
|
||||
|
||||
* Learn transformer fine-tuning
|
||||
* Understand dataset design
|
||||
* Explore identity-mapping behavior
|
||||
* Practice Hugging Face model deployment
|
||||
* Build a foundation for future custom models
|
||||
|
||||
---
|
||||
|
||||
## 📜 License
|
||||
|
||||
Apache 2.0
|
||||
|
||||
---
|
||||
|
||||
<div align="center">
|
||||
|
||||
### Built by QuantaSparkLabs
|
||||
|
||||
</div>
|
||||
48
config.json
Normal file
48
config.json
Normal file
@@ -0,0 +1,48 @@
|
||||
{
|
||||
"_num_labels": 1,
|
||||
"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,
|
||||
"id2label": {
|
||||
"0": "LABEL_0"
|
||||
},
|
||||
"initializer_range": 0.02,
|
||||
"label2id": {
|
||||
"LABEL_0": 0
|
||||
},
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 1024,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": null,
|
||||
"n_layer": 6,
|
||||
"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": "5.10.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 50257
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": 50256,
|
||||
"transformers_version": "5.10.2"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4b7e42ef21b96b25a22522ee08e58d06f176b2405222b3e18b6dacdbee619d1a
|
||||
size 327657928
|
||||
250320
tokenizer.json
Normal file
250320
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
13
tokenizer_config.json
Normal file
13
tokenizer_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"is_local": false,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 1024,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:01ebfe4d4ae9bd1ba84f064ff96bb709ef081a33f7ec47c36379081b124b3b24
|
||||
size 5137
|
||||
Reference in New Issue
Block a user