Instructions to use NiftyOracleAI/NiftyOracle-Coder-30B 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 NiftyOracleAI/NiftyOracle-Coder-30B 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 NiftyOracleAI/NiftyOracle-Coder-30B # Run inference directly in the terminal: llama cli -hf NiftyOracleAI/NiftyOracle-Coder-30B
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf NiftyOracleAI/NiftyOracle-Coder-30B # Run inference directly in the terminal: llama cli -hf NiftyOracleAI/NiftyOracle-Coder-30B
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 NiftyOracleAI/NiftyOracle-Coder-30B # Run inference directly in the terminal: ./build/bin/llama cli -hf NiftyOracleAI/NiftyOracle-Coder-30B
Use Docker
docker model run hf.co/NiftyOracleAI/NiftyOracle-Coder-30B
- Llama new
- LM Studio
- Jan
- Ollama
How to use NiftyOracleAI/NiftyOracle-Coder-30B with Ollama:
ollama run hf.co/NiftyOracleAI/NiftyOracle-Coder-30B
- Unsloth Desktop
- Docker Model Runner
How to use NiftyOracleAI/NiftyOracle-Coder-30B with Docker Model Runner:
docker model run hf.co/NiftyOracleAI/NiftyOracle-Coder-30B
- Lemonade
How to use NiftyOracleAI/NiftyOracle-Coder-30B with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull NiftyOracleAI/NiftyOracle-Coder-30B
Run and chat with the model
lemonade run user.NiftyOracle-Coder-30B-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Download sft_full_latest/adapter_config.json from NiftyOracleAI/NiftyOracle-Coder-30B: direct link, hf CLI and curl.
- Browser
- Download file 753 Bytes
-
https://huggingface.co/NiftyOracleAI/NiftyOracle-Coder-30B/resolve/main/sft_full_latest/adapter_config.json
- Command line
-
hf download hf://NiftyOracleAI/NiftyOracle-Coder-30B/sft_full_latest/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/NiftyOracleAI/NiftyOracle-Coder-30B/resolve/main/sft_full_latest/adapter_config.json
753 Bytes
| { | |
| "alpha_pattern": {}, | |
| "auto_mapping": { | |
| "base_model_class": "CodeSymb1B", | |
| "parent_library": "codesymb_OneBillion_Conversation" | |
| }, | |
| "base_model_name_or_path": null, | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 200, | |
| "lora_dropout": 0.0, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 100, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "d", | |
| "g", | |
| "u", | |
| "q", | |
| "k", | |
| "o", | |
| "v" | |
| ], | |
| "task_type": null, | |
| "use_dora": false, | |
| "use_rslora": false | |
| } |