Instructions to use Macmill/Fyve-AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Macmill/Fyve-AI with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Macmill/Fyve-AI", filename="fyve-ai.Q4_K_M.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use Macmill/Fyve-AI with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Macmill/Fyve-AI:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Macmill/Fyve-AI:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Macmill/Fyve-AI:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Macmill/Fyve-AI: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 Macmill/Fyve-AI:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Macmill/Fyve-AI: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 Macmill/Fyve-AI:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Macmill/Fyve-AI:Q4_K_M
Use Docker
docker model run hf.co/Macmill/Fyve-AI:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Macmill/Fyve-AI with Ollama:
ollama run hf.co/Macmill/Fyve-AI:Q4_K_M
- Unsloth Studio new
How to use Macmill/Fyve-AI 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 Macmill/Fyve-AI 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 Macmill/Fyve-AI to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Macmill/Fyve-AI to start chatting
- Docker Model Runner
How to use Macmill/Fyve-AI with Docker Model Runner:
docker model run hf.co/Macmill/Fyve-AI:Q4_K_M
- Lemonade
How to use Macmill/Fyve-AI with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Macmill/Fyve-AI:Q4_K_M
Run and chat with the model
lemonade run user.Fyve-AI-Q4_K_M
List all available models
lemonade list
Trained with Unsloth - config
Browse files- config.json +73 -0
config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"torch_dtype": "float16",
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2560,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 9728,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention"
|
| 52 |
+
],
|
| 53 |
+
"max_position_embeddings": 262144,
|
| 54 |
+
"max_window_layers": 36,
|
| 55 |
+
"model_name": "unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit",
|
| 56 |
+
"model_type": "qwen3",
|
| 57 |
+
"num_attention_heads": 32,
|
| 58 |
+
"num_hidden_layers": 36,
|
| 59 |
+
"num_key_value_heads": 8,
|
| 60 |
+
"pad_token_id": 151669,
|
| 61 |
+
"rms_norm_eps": 1e-06,
|
| 62 |
+
"rope_parameters": {
|
| 63 |
+
"rope_theta": 5000000,
|
| 64 |
+
"rope_type": "default"
|
| 65 |
+
},
|
| 66 |
+
"sliding_window": null,
|
| 67 |
+
"tie_word_embeddings": true,
|
| 68 |
+
"unsloth_fixed": true,
|
| 69 |
+
"unsloth_version": "2026.3.8",
|
| 70 |
+
"use_cache": false,
|
| 71 |
+
"use_sliding_window": false,
|
| 72 |
+
"vocab_size": 151936
|
| 73 |
+
}
|