Text Generation
MLX
Safetensors
English
phi
phi-2
html
css
web-development
code-generation
fine-tuned
apple-silicon
conversational
4-bit precision
Instructions to use nexsendev/webicoder-v3-mlx-q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use nexsendev/webicoder-v3-mlx-q4 with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("nexsendev/webicoder-v3-mlx-q4") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use nexsendev/webicoder-v3-mlx-q4 with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "nexsendev/webicoder-v3-mlx-q4"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "nexsendev/webicoder-v3-mlx-q4" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "nexsendev/webicoder-v3-mlx-q4", "messages": [ {"role": "user", "content": "Hello"} ] }'
| { | |
| "architectures": [ | |
| "PhiForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 50256, | |
| "dtype": "float16", | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 50256, | |
| "hidden_act": "gelu_new", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 10240, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 4096, | |
| "model_type": "phi", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 50256, | |
| "partial_rotary_factor": 0.4, | |
| "qk_layernorm": false, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine" | |
| }, | |
| "resid_pdrop": 0.1, | |
| "rope_parameters": { | |
| "partial_rotary_factor": 0.4, | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.0.0", | |
| "use_cache": true, | |
| "vocab_size": 51200 | |
| } |