Text Generation
PyTorch
GGUF
Japanese
English
japanese
little-language-model
tiny-language-model
edge-ai
embedded-ai
ex-word
llama-cpp
lm-studio
custom-code
conversational
Instructions to use ToTo-40417/EXLLM-ONI5M 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 ToTo-40417/EXLLM-ONI5M 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 ToTo-40417/EXLLM-ONI5M:F16 # Run inference directly in the terminal: llama cli -hf ToTo-40417/EXLLM-ONI5M:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf ToTo-40417/EXLLM-ONI5M:F16 # Run inference directly in the terminal: llama cli -hf ToTo-40417/EXLLM-ONI5M:F16
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 ToTo-40417/EXLLM-ONI5M:F16 # Run inference directly in the terminal: ./build/bin/llama cli -hf ToTo-40417/EXLLM-ONI5M:F16
Use Docker
docker model run hf.co/ToTo-40417/EXLLM-ONI5M:F16
- Llama new
- LM Studio
- Jan
- vLLM
How to use ToTo-40417/EXLLM-ONI5M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ToTo-40417/EXLLM-ONI5M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ToTo-40417/EXLLM-ONI5M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ToTo-40417/EXLLM-ONI5M:F16
- Ollama
How to use ToTo-40417/EXLLM-ONI5M with Ollama:
ollama run hf.co/ToTo-40417/EXLLM-ONI5M:F16
- Unsloth Desktop
- Docker Model Runner
How to use ToTo-40417/EXLLM-ONI5M with Docker Model Runner:
docker model run hf.co/ToTo-40417/EXLLM-ONI5M:F16
- Lemonade
How to use ToTo-40417/EXLLM-ONI5M with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ToTo-40417/EXLLM-ONI5M:F16
Run and chat with the model
lemonade run user.EXLLM-ONI5M-F16
List all available models
lemonade list
- Atomic Chat
Download lmstudio/training_manifest.json from ToTo-40417/EXLLM-ONI5M: direct link, hf CLI and curl.
- Browser
- Download file 2.76 kB
-
https://huggingface.co/ToTo-40417/EXLLM-ONI5M/resolve/main/lmstudio/training_manifest.json
- Command line
-
hf download hf://ToTo-40417/EXLLM-ONI5M/lmstudio/training_manifest.json
-
curl -L -o training_manifest.json https://huggingface.co/ToTo-40417/EXLLM-ONI5M/resolve/main/lmstudio/training_manifest.json
2.76 kB
| { | |
| "name": "EXLLM-ONI5M-GGUF-companion", | |
| "relationship": "separately trained Llama-compatible companion; not converted EX-word weights", | |
| "parameters": 5441184, | |
| "architecture": { | |
| "family": "LlamaForCausalLM", | |
| "layers": 6, | |
| "hidden_size": 288, | |
| "intermediate_size": 608, | |
| "attention_heads": 9, | |
| "kv_heads": 9, | |
| "training_sequence_length": 128, | |
| "runtime_context_length": 512, | |
| "vocabulary_size": 1024 | |
| }, | |
| "training_records_including_overlaps": 31842, | |
| "validation_records": 2260, | |
| "training_files": [ | |
| { | |
| "path": "oni5m/data/stage1.jsonl", | |
| "bytes": 1514468, | |
| "sha256": "9ec74f90fbf2066e7d7722af400bb69bad0730b8cd5776eba5ba97b7bd742b60" | |
| }, | |
| { | |
| "path": "oni5m/data/train_balanced.jsonl", | |
| "bytes": 2318131, | |
| "sha256": "6c4f34db49f5d0cd9a3b825628b763f58685ba2b6ba747f119b6d4e43100c5ef" | |
| }, | |
| { | |
| "path": "oni5m/data/stage3.jsonl", | |
| "bytes": 1023877, | |
| "sha256": "cdba024563f1dcb975fae9119443ee528556e278a61b960415345fbd901247c9" | |
| }, | |
| { | |
| "path": "oni5m/data/stage4_repair.jsonl", | |
| "bytes": 1429497, | |
| "sha256": "3fb386a2936a4133ea52e78ad4f43afb175116b909ad9e3b70488e8dc7db501f" | |
| }, | |
| { | |
| "path": "oni5m/data/stage5_mathop.jsonl", | |
| "bytes": 175437, | |
| "sha256": "128f4d9845b49d44e6f8307ddf76abba16cbed2a3d0daecca34750df7588c6e9" | |
| } | |
| ], | |
| "validation_file": { | |
| "path": "oni5m/data/valid.jsonl", | |
| "bytes": 447620, | |
| "sha256": "fc37b3240a61cde4503f0bd340a94cb813837ce0235e47d47d80dc1f3eac49b8" | |
| }, | |
| "processed_sequence_tokens": 7154830, | |
| "epochs": 10, | |
| "steps": 2490, | |
| "best_validation_loss": 1.4717197205131836, | |
| "seed": 20261002, | |
| "history": [ | |
| { | |
| "epoch": 1, | |
| "valid_loss": 1.4717197205131836, | |
| "seconds": 11.116554498672485 | |
| }, | |
| { | |
| "epoch": 2, | |
| "valid_loss": 1.5578404308833764, | |
| "seconds": 20.62734866142273 | |
| }, | |
| { | |
| "epoch": 3, | |
| "valid_loss": 1.742609938110946, | |
| "seconds": 30.06829810142517 | |
| }, | |
| { | |
| "epoch": 4, | |
| "valid_loss": 1.6804442983478163, | |
| "seconds": 39.48585367202759 | |
| }, | |
| { | |
| "epoch": 5, | |
| "valid_loss": 1.7555806212697047, | |
| "seconds": 48.923298835754395 | |
| }, | |
| { | |
| "epoch": 6, | |
| "valid_loss": 1.743759198982372, | |
| "seconds": 58.34962177276611 | |
| }, | |
| { | |
| "epoch": 7, | |
| "valid_loss": 1.7552301105815065, | |
| "seconds": 67.88318419456482 | |
| }, | |
| { | |
| "epoch": 8, | |
| "valid_loss": 1.848393173895262, | |
| "seconds": 77.23627734184265 | |
| }, | |
| { | |
| "epoch": 9, | |
| "valid_loss": 1.8836381879996107, | |
| "seconds": 86.8110785484314 | |
| }, | |
| { | |
| "epoch": 10, | |
| "valid_loss": 1.9468267523296512, | |
| "seconds": 96.28844380378723 | |
| } | |
| ] | |
| } | |