Instructions to use madhuHuggingface/functiongemma-ec2-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use madhuHuggingface/functiongemma-ec2-finetuned with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("madhuHuggingface/functiongemma-ec2-finetuned", dtype="auto")

llama-cpp-python

How to use madhuHuggingface/functiongemma-ec2-finetuned with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="madhuHuggingface/functiongemma-ec2-finetuned",
	filename="gguf/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 madhuHuggingface/functiongemma-ec2-finetuned with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf madhuHuggingface/functiongemma-ec2-finetuned:Q8_0
# Run inference directly in the terminal:
llama-cli -hf madhuHuggingface/functiongemma-ec2-finetuned:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf madhuHuggingface/functiongemma-ec2-finetuned:Q8_0
# Run inference directly in the terminal:
llama-cli -hf madhuHuggingface/functiongemma-ec2-finetuned: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 madhuHuggingface/functiongemma-ec2-finetuned:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf madhuHuggingface/functiongemma-ec2-finetuned: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 madhuHuggingface/functiongemma-ec2-finetuned:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf madhuHuggingface/functiongemma-ec2-finetuned:Q8_0

Use Docker

docker model run hf.co/madhuHuggingface/functiongemma-ec2-finetuned:Q8_0

LM Studio
Jan
Ollama
How to use madhuHuggingface/functiongemma-ec2-finetuned with Ollama:
```
ollama run hf.co/madhuHuggingface/functiongemma-ec2-finetuned:Q8_0
```

Unsloth Studio

How to use madhuHuggingface/functiongemma-ec2-finetuned 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 madhuHuggingface/functiongemma-ec2-finetuned 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 madhuHuggingface/functiongemma-ec2-finetuned to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for madhuHuggingface/functiongemma-ec2-finetuned to start chatting

How to use madhuHuggingface/functiongemma-ec2-finetuned with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf madhuHuggingface/functiongemma-ec2-finetuned: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": "madhuHuggingface/functiongemma-ec2-finetuned:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use madhuHuggingface/functiongemma-ec2-finetuned with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf madhuHuggingface/functiongemma-ec2-finetuned: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 madhuHuggingface/functiongemma-ec2-finetuned:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use madhuHuggingface/functiongemma-ec2-finetuned with Docker Model Runner:
```
docker model run hf.co/madhuHuggingface/functiongemma-ec2-finetuned:Q8_0
```

Lemonade

How to use madhuHuggingface/functiongemma-ec2-finetuned with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull madhuHuggingface/functiongemma-ec2-finetuned:Q8_0

Run and chat with the model

lemonade run user.functiongemma-ec2-finetuned-Q8_0

List all available models

lemonade list

madhuHuggingface commited on Apr 24

Commit

8a468dd

verified ·

1 Parent(s): 5403dd4

Training in progress, step 700, checkpoint

Browse files

Files changed (4) hide show

last-checkpoint/adapter_model.safetensors +1 -1
last-checkpoint/optimizer.pt +1 -1
last-checkpoint/scheduler.pt +1 -1
last-checkpoint/trainer_state.json +73 -3

last-checkpoint/adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac7cc399e9e803e832d3e4a887b8e17a2bca991693fd5fedaf23f9a68a33002
 size 60785144

 version https://git-lfs.github.com/spec/v1
+oid sha256:303343475309841b85eed76df986b9e6645cec918e116af2f899f51b3ecf6251
 size 60785144

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f004ecba8cf08197c7c0bc5a876982d8a5c63197217f74df63c2ea81b3e5c3
 size 31149205

 version https://git-lfs.github.com/spec/v1
+oid sha256:4fde37edca5adb4005644c406622925ee8e2714e074424bc24af3f6441bbc502
 size 31149205

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:863116f078b55fcd26c21f209dcf85d6cb8d8e08cee3e74f49dae023ed260e47
 size 1465

 version https://git-lfs.github.com/spec/v1
+oid sha256:ff4532c1ad6082d83324dc653af69e29d03fa02637d181855b2e21b79b948367
 size 1465

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.4,
   "eval_steps": 500,
-  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -428,6 +428,76 @@
       "learning_rate": 2.038171362173843e-05,
       "loss": 0.0118,
       "step": 600
     }
   ],
   "logging_steps": 10,
@@ -447,7 +517,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1918926157158912.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 2.8,
   "eval_steps": 500,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "learning_rate": 2.038171362173843e-05,
       "loss": 0.0118,
       "step": 600
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.3860418498516083,
+      "learning_rate": 1.7852344669758593e-05,
+      "loss": 0.0108,
+      "step": 610
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.0032947103027254343,
+      "learning_rate": 1.547509426469368e-05,
+      "loss": 0.0132,
+      "step": 620
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.1931905448436737,
+      "learning_rate": 1.325436452704033e-05,
+      "loss": 0.0165,
+      "step": 630
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.12002695351839066,
+      "learning_rate": 1.119426773705068e-05,
+      "loss": 0.0086,
+      "step": 640
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.004515103995800018,
+      "learning_rate": 9.298618719736418e-06,
+      "loss": 0.0042,
+      "step": 650
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.015484682284295559,
+      "learning_rate": 7.570927780690673e-06,
+      "loss": 0.0114,
+      "step": 660
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.038616035133600235,
+      "learning_rate": 6.0143942058104695e-06,
+      "loss": 0.0053,
+      "step": 670
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.19781313836574554,
+      "learning_rate": 4.631900336955441e-06,
+      "loss": 0.0093,
+      "step": 680
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.23140157759189606,
+      "learning_rate": 3.426006234514523e-06,
+      "loss": 0.009,
+      "step": 690
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.21433651447296143,
+      "learning_rate": 2.39894493676317e-06,
+      "loss": 0.0117,
+      "step": 700
     }
   ],
   "logging_steps": 10,
       "attributes": {}
     }
   },
+  "total_flos": 2236049469769728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null