Instructions to use luezr/moonkaAI 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 luezr/moonkaAI 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 luezr/moonkaAI:Q4_K_M # Run inference directly in the terminal: llama cli -hf luezr/moonkaAI:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf luezr/moonkaAI:Q4_K_M # Run inference directly in the terminal: llama cli -hf luezr/moonkaAI:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf luezr/moonkaAI:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf luezr/moonkaAI:Q4_K_M
Use Docker
docker model run hf.co/luezr/moonkaAI:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use luezr/moonkaAI with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "luezr/moonkaAI" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "luezr/moonkaAI", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/luezr/moonkaAI:Q4_K_M
- Ollama
How to use luezr/moonkaAI with Ollama:
ollama run hf.co/luezr/moonkaAI:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use luezr/moonkaAI with Docker Model Runner:
docker model run hf.co/luezr/moonkaAI:Q4_K_M
- Lemonade
How to use luezr/moonkaAI with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull luezr/moonkaAI:Q4_K_M
Run and chat with the model
lemonade run user.moonkaAI-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,23 +1,79 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
tags:
|
|
|
|
| 3 |
- gguf
|
| 4 |
-
-
|
|
|
|
| 5 |
- unsloth
|
| 6 |
-
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
-
|
| 14 |
-
- For text only LLMs: `llama-cli -hf luezr/moonkaAI --jinja`
|
| 15 |
-
- For multimodal models: `llama-mtmd-cli -hf luezr/moonkaAI --jinja`
|
| 16 |
|
| 17 |
-
|
| 18 |
-
|
|
|
|
| 19 |
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
|
| 23 |
-
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- ru
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
base_model: unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit
|
| 6 |
tags:
|
| 7 |
+
- text-generation
|
| 8 |
- gguf
|
| 9 |
+
- q4_k_m
|
| 10 |
+
- lora
|
| 11 |
- unsloth
|
| 12 |
+
- chatml
|
| 13 |
+
datasets:
|
| 14 |
+
- d0rj/ru-instruct
|
| 15 |
---
|
| 16 |
|
| 17 |
+
# MoonkaAI
|
| 18 |
+
|
| 19 |
+
Локальная русскоязычная языковая модель для общения, развлечений, простых объяснений и лёгкого сарказма.
|
| 20 |
+
|
| 21 |
+
## Параметры
|
| 22 |
+
|
| 23 |
+
- База: `unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit`
|
| 24 |
+
- Реальная база обучения: `unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit`
|
| 25 |
+
- Backend обучения: `unsloth` на `cuda`
|
| 26 |
+
- Формат диалога: ChatML (`<|im_start|>user/assistant`)
|
| 27 |
+
- LoRA rank: `16`
|
| 28 |
+
- Batch per device: `6`
|
| 29 |
+
- Gradient accumulation: `2`
|
| 30 |
+
- Effective batch: `12`
|
| 31 |
+
- Packing: `True`
|
| 32 |
+
- Gradient checkpointing: `off`
|
| 33 |
+
- Контекст обучения: `2048`
|
| 34 |
+
- Лимит входа при подготовке: `600` токенов
|
| 35 |
+
- Лимит ответа при подготовке: `1500` токенов
|
| 36 |
+
- GGUF: `q4_k_m`
|
| 37 |
+
|
| 38 |
+
## Данные
|
| 39 |
|
| 40 |
+
```json
|
| 41 |
+
{
|
| 42 |
+
"total_records": 10421,
|
| 43 |
+
"train_records": 9899,
|
| 44 |
+
"eval_records": 522,
|
| 45 |
+
"ru_records": 8000,
|
| 46 |
+
"style_records": 50,
|
| 47 |
+
"generated_style_records": 800,
|
| 48 |
+
"persona_records": 20,
|
| 49 |
+
"owner_records": 150,
|
| 50 |
+
"safety_records": 20,
|
| 51 |
+
"generated_safety_records": 680,
|
| 52 |
+
"unknown_rag_records": 400,
|
| 53 |
+
"long_text_records": 200,
|
| 54 |
+
"calculator_records": 100,
|
| 55 |
+
"smalltalk_records": 0,
|
| 56 |
+
"explain_style_records": 1,
|
| 57 |
+
"tone_records": 0,
|
| 58 |
+
"max_seq_length": 2048,
|
| 59 |
+
"max_input_tokens": 600,
|
| 60 |
+
"max_output_tokens": 1500,
|
| 61 |
+
"batch_size": 6,
|
| 62 |
+
"grad_accum": 2,
|
| 63 |
+
"effective_batch_size": 12,
|
| 64 |
+
"packing": true,
|
| 65 |
+
"gradient_checkpointing": "off",
|
| 66 |
+
"training_device": "cuda",
|
| 67 |
+
"training_backend": "unsloth",
|
| 68 |
+
"effective_base_model": "unsloth/Qwen2.5-1.5B-Instruct-bnb-4bit"
|
| 69 |
+
}
|
| 70 |
+
```
|
| 71 |
|
| 72 |
+
## Локальный запуск
|
|
|
|
|
|
|
| 73 |
|
| 74 |
+
```bash
|
| 75 |
+
python run.py --repo-id luezr/moonkaAI --threads 6 --rag auto
|
| 76 |
+
```
|
| 77 |
|
| 78 |
+
Qwen2.5-1.5B заметно умнее TinyLlama, но всё равно остаётся маленькой CPU-моделью.
|
| 79 |
+
Для более сильного качества увеличивай датасет и проверяй ответы вручную.
|
|
|
|
|
|