Text Generation
MLX
Safetensors
gemma4
apple-silicon
quantized
mixed-precision
axquant
axq
development
gemma-4
6bit
6-bit
vision
4-bit precision
Instructions to use AutomatosX/AX-gemma-4-12b-MLX-AXQ-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-gemma-4-12b-MLX-AXQ-6bit with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # if on a CUDA device, also pip install mlx[cuda] # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("AutomatosX/AX-gemma-4-12b-MLX-AXQ-6bit") prompt = "Once upon a time in" text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- MLX LM
How to use AutomatosX/AX-gemma-4-12b-MLX-AXQ-6bit with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Generate some text mlx_lm.generate --model "AutomatosX/AX-gemma-4-12b-MLX-AXQ-6bit" --prompt "Once upon a time"
Refresh development model card and public provenance (axquant_quantizer_execution.json)
f32d3e9 verified | { | |
| "created_at": "2026-08-02T18:30:09.094072Z", | |
| "plan_sha256": "eb5a0df3d5161f0f00224c2dab68a065d36209a68b7973706add0c61c5cbb0cd", | |
| "records": [ | |
| { | |
| "bits": 8, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.embed_tokens", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.11.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.11.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.11.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.11.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.11.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.11.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.15.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.15.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.15.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.15.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.15.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.15.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.15.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.17.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.17.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.17.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.17.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.17.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.17.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.19.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.19.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.19.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.19.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.19.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.19.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.19.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.23.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.23.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.23.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.23.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.23.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.23.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.27.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.27.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.27.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.27.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.27.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.27.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.27.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.29.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.29.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.29.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.29.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.29.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.29.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.3.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.3.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.3.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.3.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.3.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.3.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.3.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.31.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.31.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.31.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.31.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.31.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.31.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.31.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.32.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.32.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.32.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.32.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.32.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.32.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.32.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.33.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.33.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.33.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.33.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.33.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.33.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.33.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.34.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.34.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.34.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.34.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.34.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.34.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.34.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.35.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.35.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.35.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.35.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.35.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.35.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.36.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.36.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.36.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.36.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.36.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.36.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.36.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.37.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.37.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.37.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.37.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.37.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.37.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.37.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 4, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.38.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.38.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.38.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.38.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.38.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.38.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.38.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.39.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.39.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.39.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.39.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.39.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.39.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.39.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.40.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.40.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.40.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.40.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.40.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.40.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.40.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.41.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.41.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.41.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.41.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.41.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.41.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.42.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.42.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.42.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.42.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.42.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.42.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.42.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.43.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.43.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.43.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.43.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.43.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.43.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.43.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.44.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.44.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.44.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.44.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.44.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.44.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.44.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.45.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.45.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.45.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.45.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.45.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.45.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.45.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.46.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.46.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.46.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.46.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.46.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.46.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.46.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.47.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.47.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.47.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.47.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.47.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.47.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.5.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.5.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.5.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.5.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.5.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.5.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.6.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.6.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.6.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.6.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.6.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.6.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.6.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.7.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.7.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.7.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.7.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.7.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.7.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.7.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.9.mlp.down_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.9.mlp.gate_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 64, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.9.mlp.up_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.9.self_attn.k_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.9.self_attn.o_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.9.self_attn.q_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.9.self_attn.v_proj", | |
| "note": "MLX-LM affine packing", | |
| "success": true | |
| } | |
| ], | |
| "schema_version": "axquant.quantizer-execution.v1" | |
| } | |