Instructions to use Noeai/IPAFuzzylamav5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Noeai/IPAFuzzylamav5 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Noeai/IPAFuzzylamav5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Noeai/IPAFuzzylamav5 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 Noeai/IPAFuzzylamav5:Q8_0 # Run inference directly in the terminal: llama cli -hf Noeai/IPAFuzzylamav5:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Noeai/IPAFuzzylamav5:Q8_0 # Run inference directly in the terminal: llama cli -hf Noeai/IPAFuzzylamav5:Q8_0
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 Noeai/IPAFuzzylamav5:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf Noeai/IPAFuzzylamav5:Q8_0
Use Docker
docker model run hf.co/Noeai/IPAFuzzylamav5:Q8_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use Noeai/IPAFuzzylamav5 with Ollama:
ollama run hf.co/Noeai/IPAFuzzylamav5:Q8_0
- Unsloth Desktop
- Pi
How to use Noeai/IPAFuzzylamav5 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Noeai/IPAFuzzylamav5:Q8_0
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Noeai/IPAFuzzylamav5:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Noeai/IPAFuzzylamav5 with Docker Model Runner:
docker model run hf.co/Noeai/IPAFuzzylamav5:Q8_0
- Lemonade
How to use Noeai/IPAFuzzylamav5 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Noeai/IPAFuzzylamav5:Q8_0
Run and chat with the model
lemonade run user.IPAFuzzylamav5-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use Noeai/IPAFuzzylamav5 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Noeai/IPAFuzzylamav5: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://127.0.0.1:9931/v1 hermes config set model.default Noeai/IPAFuzzylamav5:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Noeai/IPAFuzzylamav5 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Noeai/IPAFuzzylamav5:Q8_0
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "Noeai/IPAFuzzylamav5:Q8_0" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,38 @@ license: apache-2.0
|
|
| 10 |
language:
|
| 11 |
- en
|
| 12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
# Uploaded model
|
| 15 |
|
|
@@ -17,6 +49,6 @@ language:
|
|
| 17 |
- **License:** apache-2.0
|
| 18 |
- **Finetuned from model :** unsloth/llama-3.2-1b-instruct-bnb-4bit
|
| 19 |
|
| 20 |
-
|
| 21 |
|
| 22 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
|
|
|
| 10 |
language:
|
| 11 |
- en
|
| 12 |
---
|
| 13 |
+
# IPAFuzzv1amav5: Fine-tuned LLaMA 3.2 (1B) for IPA Pronunciations
|
| 14 |
+
|
| 15 |
+
## Overview
|
| 16 |
+
IPAFuzzv1amav5 is a fine-tuned LLaMA 3.2 (1B) model trained using Unsloth to generate all possible pronunciations in the International Phonetic Alphabet (IPA) for a given name spelled in English script.
|
| 17 |
+
|
| 18 |
+
## Features
|
| 19 |
+
- Generates multiple possible IPA transcriptions for a given name
|
| 20 |
+
- Handles regional and dialectal variations
|
| 21 |
+
- Supports ambiguous spellings
|
| 22 |
+
- Efficient inference with optimized fine-tuning via Unsloth
|
| 23 |
+
|
| 24 |
+
## Model Details
|
| 25 |
+
- **Base Model:** LLaMA 3.2 (1B)
|
| 26 |
+
- **Fine-tuning Framework:** Unsloth
|
| 27 |
+
- **Training Data:** Names with known IPA transcriptions from multiple linguistic sources
|
| 28 |
+
- **Objective:** Predict all phonetic variations for a given input name
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
## Example Outputs
|
| 32 |
+
| Name | IPA Transcriptions |
|
| 33 |
+
|-------|-------------------|
|
| 34 |
+
| Alice | /ˈælɪs/, /ˈeɪlɪs/, /ˈælɪs/ |
|
| 35 |
+
| John | /dʒɒn/, /dʒɔn/, /dʒɑn/ |
|
| 36 |
+
|
| 37 |
+
## License
|
| 38 |
+
MIT License
|
| 39 |
+
|
| 40 |
+
## Acknowledgments
|
| 41 |
+
- Meta for LLaMA 3.2
|
| 42 |
+
- Unsloth for efficient model fine-tuning
|
| 43 |
+
- Open-source linguistic datasets
|
| 44 |
+
|
| 45 |
|
| 46 |
# Uploaded model
|
| 47 |
|
|
|
|
| 49 |
- **License:** apache-2.0
|
| 50 |
- **Finetuned from model :** unsloth/llama-3.2-1b-instruct-bnb-4bit
|
| 51 |
|
| 52 |
+
|
| 53 |
|
| 54 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|