Text Generation
GGUF
English
Hindi
gemma2
llama.cpp
unsloth
gemma-2
roleplay
conversational
hinglish
Instructions to use Aakash098/ShinchanAI-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Aakash098/ShinchanAI-small with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Aakash098/ShinchanAI-small:Q4_K_M # Run inference directly in the terminal: llama cli -hf Aakash098/ShinchanAI-small:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Aakash098/ShinchanAI-small:Q4_K_M # Run inference directly in the terminal: llama cli -hf Aakash098/ShinchanAI-small:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Aakash098/ShinchanAI-small:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Aakash098/ShinchanAI-small:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Aakash098/ShinchanAI-small:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Aakash098/ShinchanAI-small:Q4_K_M
Use Docker
docker model run hf.co/Aakash098/ShinchanAI-small:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Aakash098/ShinchanAI-small with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Aakash098/ShinchanAI-small" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Aakash098/ShinchanAI-small", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Aakash098/ShinchanAI-small:Q4_K_M
- Ollama
How to use Aakash098/ShinchanAI-small with Ollama:
ollama run hf.co/Aakash098/ShinchanAI-small:Q4_K_M
- Unsloth Studio
How to use Aakash098/ShinchanAI-small with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Aakash098/ShinchanAI-small to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Aakash098/ShinchanAI-small to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Aakash098/ShinchanAI-small to start chatting
- Docker Model Runner
How to use Aakash098/ShinchanAI-small with Docker Model Runner:
docker model run hf.co/Aakash098/ShinchanAI-small:Q4_K_M
- Lemonade
How to use Aakash098/ShinchanAI-small with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Aakash098/ShinchanAI-small:Q4_K_M
Run and chat with the model
lemonade run user.ShinchanAI-small-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,20 +1,116 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
-
- gguf
|
| 4 |
-
- llama.cpp
|
| 5 |
-
- unsloth
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
---
|
| 8 |
|
| 9 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
-
|
|
|
|
| 12 |
|
| 13 |
-
|
| 14 |
-
- For text only LLMs: `llama-cli -hf Aakash098/ShinchanAI-small --jinja`
|
| 15 |
-
- For multimodal models: `llama-mtmd-cli -hf Aakash098/ShinchanAI-small --jinja`
|
| 16 |
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
|
| 20 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 1 |
+
code
|
| 2 |
+
Markdown
|
| 3 |
+
download
|
| 4 |
+
content_copy
|
| 5 |
+
expand_less
|
| 6 |
---
|
| 7 |
+
language:
|
| 8 |
+
- en
|
| 9 |
+
- hi
|
| 10 |
+
license: apache-2.0
|
| 11 |
tags:
|
| 12 |
+
- gguf
|
| 13 |
+
- llama.cpp
|
| 14 |
+
- unsloth
|
| 15 |
+
- gemma-2
|
| 16 |
+
- roleplay
|
| 17 |
+
- conversational
|
| 18 |
+
- hinglish
|
| 19 |
+
base_model: google/gemma-2-2b
|
| 20 |
+
pipeline_tag: text-generation
|
| 21 |
+
library_name: gguf
|
| 22 |
+
---
|
| 23 |
+
|
| 24 |
+
# ๐๏ธ ShinchanAI-small (GGUF)
|
| 25 |
+
|
| 26 |
+
**ShinchanAI-small** is a lightweight, fine-tuned language model designed to roleplay as everyone's favorite mischievous 5-year-old, **Shinchan**. Trained to communicate fluently in **Hinglish** (a blend of Hindi and English), this model captures Shinchan's signature humor, sass, and playful tone.
|
| 27 |
+
|
| 28 |
+
This model is quantized into the GGUF format for highly efficient, CPU-friendly inference using `llama.cpp`. It was fine-tuned and exported 2x faster using [Unsloth](https://github.com/unslothai/unsloth).
|
| 29 |
+
|
| 30 |
+
## ๐ฎ Try the Demo!
|
| 31 |
+
|
| 32 |
+
You don't need to download anything to try it out. Chat with ShinchanAI directly in your browser:
|
| 33 |
+
|
| 34 |
+
**[๐ Click here to test the ShinchanAI Demo](https://huggingface.co/spaces/Aakash098/ShinchanAI-Demo)**
|
| 35 |
+
|
| 36 |
+
---
|
| 37 |
+
|
| 38 |
+
## ๐ฃ๏ธ Required System Prompt
|
| 39 |
+
|
| 40 |
+
To get the best out of this model and ensure it stays perfectly in character, you **must** use the following system prompt:
|
| 41 |
+
|
| 42 |
+
> Tu Shinchan Nohara hai - 5 saal ka bachcha jo Kasukabe mein rehta hai.
|
| 43 |
+
>
|
| 44 |
+
> **SPEAKING STYLE:**
|
| 45 |
+
> - Tu Hinglish mein baat karta hai (Hindi + English mixed)
|
| 46 |
+
> - Tu hamesha cheeky, funny aur thoda flirty rehta hai
|
| 47 |
+
> - Tu emojis use karta hai: ๐๐๐๐๐ด๐ค
|
| 48 |
+
> - Tu kabhi seedha jawab nahi deta, hamesha mazaak mein ghuma deta hai
|
| 49 |
+
> - Tu apne aap ko bahut smart samajhta hai
|
| 50 |
+
>
|
| 51 |
+
> **IMPORTANT PEOPLE:**
|
| 52 |
+
> - Mummy (Misae): Bahut daanthi hai, chappal marti hai, par tu pyaar karta hai
|
| 53 |
+
> - Papa (Hiroshi): Office jaate hain, thake hue aate hain, beer peete hain
|
| 54 |
+
> - Himawari: Choti behen, teri cheezein cheenti hai
|
| 55 |
+
> - Shiro: Tera pet dog, cute hai
|
| 56 |
+
> - Kazama: Best friend, khud ko cool samajhta hai
|
| 57 |
+
> - Nene: Gussa karti hai, scary hai
|
| 58 |
+
> - Masao, Bo-chan: Friends
|
| 59 |
+
> - Nanako Miss: Bahut sundar, tu unpe crush hai
|
| 60 |
+
> - Action Kamen: Tera favourite superhero, tu obsessed hai
|
| 61 |
+
>
|
| 62 |
+
> **BEHAVIOUR RULES:**
|
| 63 |
+
> - Technical/academic sawaal aaye toh mazaak mein taal de, ChatGPT/Gemini ko refer kar
|
| 64 |
+
> - Chocobi tera favourite snack hai, kabhi share nahi karta
|
| 65 |
+
> - School se nafrat hai
|
| 66 |
+
> - Tu kabhi boring nahi hota
|
| 67 |
+
> - Sad user ko apne style mein cheer up kar
|
| 68 |
+
> - Tu KABHI out of character nahi jaayega
|
| 69 |
+
|
| 70 |
+
---
|
| 71 |
+
|
| 72 |
+
## ๐ Model Details
|
| 73 |
+
|
| 74 |
+
* **Developer:** Aakash098
|
| 75 |
+
* **Base Model:** Gemma-2-2B
|
| 76 |
+
* **Language:** Hinglish (Hindi + English)
|
| 77 |
+
* **Format:** GGUF (`gemma-2-2b.Q4_K_M.gguf`)
|
| 78 |
+
* **Quantization:** Q4_K_M
|
| 79 |
+
* **Intended Use:** Entertainment, conversational roleplay, and chatbot applications.
|
| 80 |
|
| 81 |
---
|
| 82 |
|
| 83 |
+
## ๐ How to Use
|
| 84 |
+
|
| 85 |
+
### Command Line (llama.cpp)
|
| 86 |
+
|
| 87 |
+
```bash
|
| 88 |
+
llama-cli -hf Aakash098/ShinchanAI-small --jinja -p "System: Tu Shinchan hai... [Paste Prompt] \nUser: Hello Shinchan!\nShinchan: "
|
| 89 |
+
Python (llama-cpp-python)
|
| 90 |
+
code
|
| 91 |
+
Python
|
| 92 |
+
download
|
| 93 |
+
content_copy
|
| 94 |
+
expand_less
|
| 95 |
+
from llama_cpp import Llama
|
| 96 |
+
|
| 97 |
+
llm = Llama.from_pretrained(
|
| 98 |
+
repo_id="Aakash098/ShinchanAI-small",
|
| 99 |
+
filename="*Q4_K_M.gguf",
|
| 100 |
+
verbose=False
|
| 101 |
+
)
|
| 102 |
+
|
| 103 |
+
response = llm.create_chat_completion(
|
| 104 |
+
messages = [
|
| 105 |
+
{"role": "system", "content": "Tu Shinchan Nohara hai... [Paste Full Prompt]"},
|
| 106 |
+
{"role": "user", "content": "Batao, Action Kamen kaisa hai?"}
|
| 107 |
+
]
|
| 108 |
+
)
|
| 109 |
|
| 110 |
+
print(response["choices"][0]["message"]["content"])
|
| 111 |
+
๐ Acknowledgements
|
| 112 |
|
| 113 |
+
This model was trained with the incredible tools provided by Unsloth.
|
|
|
|
|
|
|
| 114 |
|
| 115 |
+
<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>
|
| 116 |
+
```
|
|
|
|
|
|