Hugging Face's logo

kcvmk
/
qwen3_4B_mlx_4bit

MLX
Safetensors
language_model
4bit
qwen3
metalrt
apple-silicon
Model card Files
xet
 Community
qwen3_4B_mlx_4bit / config.json
kcvmk's picture
kcvmk
Upload folder using huggingface_hub
5e9182c verified
raw
history blame contribute delete
168 kB
{
 "toolchain_version": "0.6.8",
 "vendor": "Alibaba",
 "family": "Qwen3",
 "name": "Qwen3-4B-MLX-4bit",
 "size": "4B",
 "quantization": "uint4",
 "repo": "Qwen/Qwen3-4B-MLX-4bit",
 "use_cases": [],
 "model_type": "language_model",
 "model_config": {
 "model_config": {
 "embedding_config": {
 "type": "MLXQuantizedTiedEmbeddingConfig",
 "input_scale": null,
 "logit_soft_cap": null,
 "group_size": 128,
 "embedding_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "transformer_config": {
 "global_rope_config": {
 "type": "UnscaledRoPEConfig",
 "precision": "bfloat16",
 "base": 1000000.0,
 "max_sequence_length": 65536
 },
 "local_rope_config": null,
 "layer_configs": [
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 },
 {
 "pre_mixer_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mixer_config": {
 "type": "AttentionConfig",
 "qkv_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "out_projection_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "query_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "key_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "num_heads": 32,
 "num_groups": 8,
 "head_dim": 128,
 "is_causal": true,
 "scale": null,
 "sliding_window_size": null,
 "logit_soft_cap": null,
 "has_sinks": false,
 "has_qkv_biases": false,
 "has_out_biases": false,
 "has_gate": false,
 "partial_rope_dim": null
 },
 "post_mixer_norm_config": null,
 "pre_mlp_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "mlp_config": {
 "type": "DenseMLPConfig",
 "linear_config": {
 "type": "MLXQuantizedLinearConfig",
 "group_size": 128,
 "weight_quantization_mode": "uint4",
 "activation_quantization_mode": null,
 "activation_precision": "bfloat16"
 },
 "activation": {
 "type": "SiLU",
 "alpha": 1.0
 },
 "has_up_biases": false,
 "has_down_biases": false,
 "gate_clipping": null,
 "up_clipping": null
 },
 "post_mlp_norm_config": null
 }
 ],
 "output_norm_config": {
 "scale_precision": "bfloat16",
 "accumulation_precision": "float32",
 "epsilon": 1e-06,
 "scale_offset": null,
 "upcast_mode": "only_normalization",
 "subtract_mean": false,
 "use_bias": false
 },
 "model_dim": 2560,
 "hidden_dim": 9728,
 "context_length": 65536
 },
 "vocab_size": 151936
 },
 "message_processor_config": {
 "prompt_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
 "output_parser_regex": "<think>(?P<chain_of_thought>.*?)(?:</think>(?P<response>.*))?\\Z",
 "system_role_name": "system",
 "user_role_name": "user",
 "assistant_role_name": "assistant",
 "eos_token": "<|im_end|>",
 "bos_token": null,
 "default_system_prompt": null
 },
 "generation_config": {
 "stop_token_ids": [
 151643,
 151645
 ],
 "temperature": 0.6,
 "top_k": 20,
 "top_p": 0.95,
 "min_p": null,
 "banned_tokens": null
 }
 },
 "grammar_start_tokens": []
}