Instructions to use YouziMa/functiongemma_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YouziMa/functiongemma_lora with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="YouziMa/functiongemma_lora",
	filename="functiongemma-270m-it.Q8_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use YouziMa/functiongemma_lora with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf YouziMa/functiongemma_lora:Q8_0
# Run inference directly in the terminal:
llama-cli -hf YouziMa/functiongemma_lora:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf YouziMa/functiongemma_lora:Q8_0
# Run inference directly in the terminal:
llama-cli -hf YouziMa/functiongemma_lora:Q8_0

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 YouziMa/functiongemma_lora:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf YouziMa/functiongemma_lora:Q8_0

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 YouziMa/functiongemma_lora:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf YouziMa/functiongemma_lora:Q8_0

Use Docker

docker model run hf.co/YouziMa/functiongemma_lora:Q8_0

LM Studio
Jan
Ollama
How to use YouziMa/functiongemma_lora with Ollama:
```
ollama run hf.co/YouziMa/functiongemma_lora:Q8_0
```

Unsloth Studio

How to use YouziMa/functiongemma_lora 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 YouziMa/functiongemma_lora 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 YouziMa/functiongemma_lora to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for YouziMa/functiongemma_lora to start chatting

How to use YouziMa/functiongemma_lora with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf YouziMa/functiongemma_lora:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "YouziMa/functiongemma_lora:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use YouziMa/functiongemma_lora with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf YouziMa/functiongemma_lora:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default YouziMa/functiongemma_lora:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use YouziMa/functiongemma_lora with Docker Model Runner:
```
docker model run hf.co/YouziMa/functiongemma_lora:Q8_0
```

Lemonade

How to use YouziMa/functiongemma_lora with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull YouziMa/functiongemma_lora:Q8_0

Run and chat with the model

lemonade run user.functiongemma_lora-Q8_0

List all available models

lemonade list

YouziMa commited on 7 days ago

Commit

2b8d268

verified ·

1 Parent(s): 4cc20c6

Trained with Unsloth - config

Browse files

Files changed (1) hide show

config.json +55 -69

config.json CHANGED Viewed

@@ -1,70 +1,56 @@
 {
-  "_sliding_window_pattern": 6,
-  "architectures": [
-    "Gemma3ForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "attn_logit_softcapping": null,
-  "bos_token_id": 2,
-  "dtype": "float16",
-  "eos_token_id": 106,
-  "final_logit_softcapping": null,
-  "head_dim": 256,
-  "hidden_activation": "gelu_pytorch_tanh",
-  "hidden_size": 640,
-  "initializer_range": 0.02,
-  "intermediate_size": 2048,
-  "layer_types": [
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "full_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "sliding_attention",
-    "full_attention"
-  ],
-  "max_position_embeddings": 32768,
-  "model_name": "unsloth/functiongemma-270m-it-unsloth-bnb-4bit",
-  "model_type": "gemma3_text",
-  "num_attention_heads": 4,
-  "num_hidden_layers": 18,
-  "num_key_value_heads": 1,
-  "pad_token_id": 0,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
-  "query_pre_attn_scalar": 256,
-  "rms_norm_eps": 1e-06,
-  "rope_local_base_freq": 10000.0,
-  "rope_parameters": null,
-  "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": 512,
-  "transformers_version": "4.56.2",
-  "unsloth_fixed": true,
-  "unsloth_version": "2026.5.2",
-  "use_bidirectional_attention": false,
-  "use_cache": true,
-  "vocab_size": 262144
-}

 {
+    "_sliding_window_pattern": 6,
+    "architectures": [
+        "Gemma3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "torch_dtype": "float16",
+    "eos_token_id": 106,
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 640,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "layer_types": [
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "model_name": "unsloth/functiongemma-270m-it",
+    "model_type": "gemma3_text",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 18,
+    "num_key_value_heads": 1,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sliding_window": 512,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.5.8",
+    "use_bidirectional_attention": false,
+    "use_cache": true,
+    "vocab_size": 262144
+}