Instructions to use AutomatosX/AX-Clef-Flash-9B-MLX-AXQ-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-Clef-Flash-9B-MLX-AXQ-6bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download AutomatosX/AX-Clef-Flash-9B-MLX-AXQ-6bit --local-dir AX-Clef-Flash-9B-MLX-AXQ-6bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download axquant_quantizer_execution.json from AutomatosX/AX-Clef-Flash-9B-MLX-AXQ-6bit: direct link, hf CLI and curl.
- Browser
- Download file 65.1 kB
-
https://huggingface.co/AutomatosX/AX-Clef-Flash-9B-MLX-AXQ-6bit/resolve/main/axquant_quantizer_execution.json
- Command line
-
hf download hf://AutomatosX/AX-Clef-Flash-9B-MLX-AXQ-6bit/axquant_quantizer_execution.json
-
curl -L -o axquant_quantizer_execution.json https://huggingface.co/AutomatosX/AX-Clef-Flash-9B-MLX-AXQ-6bit/resolve/main/axquant_quantizer_execution.json
65.1 kB
| { | |
| "created_at": "2026-10-24T05:45:18.927067Z", | |
| "plan_sha256": "7b1afa6c8e79dda3cdea9379b202a5cabab8945b1da1a52de2bd627d029de8ab", | |
| "records": [ | |
| { | |
| "bits": 8, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.embed_tokens", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 8, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 8, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 8, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.0.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 8, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 8, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.1.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 8, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 8, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.10.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.11.mlp.down_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.11.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.11.self_attn.v_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 8, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 8, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.12.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 8, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.13.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.2.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.3.mlp.down_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.3.self_attn.v_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.4.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.5.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.5.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.5.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.5.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.5.linear_attn.out_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.mlp.down_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.mlp.gate_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.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.6.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.6.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.6.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.6.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.6.linear_attn.out_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.mlp.down_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.mlp.gate_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.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.mlp.down_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.mlp.gate_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.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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.8.linear_attn.out_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.mlp.down_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.mlp.gate_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.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.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.9.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.9.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.9.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.9.linear_attn.out_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.mlp.down_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.mlp.gate_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.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.13.mlp.gate_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.14.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.15.mlp.down_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.15.self_attn.v_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.16.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.17.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.17.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.17.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.17.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.17.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.18.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.19.mlp.down_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.19.self_attn.v_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.20.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.21.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.22.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.23.mlp.down_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.23.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.23.self_attn.v_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.24.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.25.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.26.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.27.mlp.down_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.27.self_attn.v_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.28.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.29.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.29.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.29.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.29.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.29.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.linear_attn.in_proj_a", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.linear_attn.in_proj_b", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.linear_attn.in_proj_qkv", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.linear_attn.in_proj_z", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "fallback": false, | |
| "group_size": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.30.linear_attn.out_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 6, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.31.mlp.down_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| }, | |
| { | |
| "bits": 6, | |
| "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": 6, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "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": 32, | |
| "metadata": {}, | |
| "method": "affine", | |
| "module_path": "model.language_model.layers.31.self_attn.v_proj", | |
| "note": "mlx-lm affine packing", | |
| "success": true | |
| } | |
| ], | |
| "schema_version": "axquant.quantizer-execution.v2" | |
| } | |