Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

BiCodec/config.yaml

@@ -0,0 +1,60 @@
+audio_tokenizer:
+  mel_params:
+    sample_rate: 16000
+    n_fft: 1024
+    win_length: 640
+    hop_length: 320
+    mel_fmin: 10 
+    mel_fmax: null
+    num_mels: 128
+
+  encoder:
+    input_channels: 1024
+    vocos_dim: 384
+    vocos_intermediate_dim: 2048
+    vocos_num_layers: 12
+    out_channels: 1024
+    sample_ratios: [1,1]
+
+  decoder:
+    input_channel: 1024
+    channels: 1536
+    rates: [8, 5, 4, 2]
+    kernel_sizes: [16,11,8,4]
+
+  quantizer:
+    input_dim: 1024
+    codebook_size: 8192
+    codebook_dim: 8
+    commitment: 0.25
+    codebook_loss_weight: 2.0
+    use_l2_normlize: True
+    threshold_ema_dead_code: 0.2
+  
+  speaker_encoder:
+    input_dim: 128
+    out_dim: 1024
+    latent_dim: 128
+    token_num: 32
+    fsq_levels: [4, 4, 4, 4, 4, 4]
+    fsq_num_quantizers: 1
+
+  prenet:
+    input_channels: 1024
+    vocos_dim: 384
+    vocos_intermediate_dim: 2048
+    vocos_num_layers: 12
+    out_channels: 1024
+    condition_dim: 1024
+    sample_ratios: [1,1]
+    use_tanh_at_final: False
+
+  postnet: 
+    input_channels: 1024
+    vocos_dim: 384
+    vocos_intermediate_dim: 2048
+    vocos_num_layers: 6
+    out_channels: 1024
+    use_tanh_at_final: False
+
+

BiCodec/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9940cd48d4446e4340ced82d234bf5618350dd9f5db900ebe47a4fdb03867ec
+size 625518756

README.md

@@ -0,0 +1,23 @@
+---
+license: cc-by-nc-sa-4.0
+language:
+- en
+- zh
+tags:
+- text-to-speech
+- mlx
+library_tag: spark-tts
+---
+
+# mlx-community/Spark-TTS-0.5B-4-6bit
+This model was converted to MLX format from [`prince-canuma/Spark-TTS-0.5B`](https://huggingface.co/prince-canuma/Spark-TTS-0.5B) using mlx-audio version **0.2.0**.
+Refer to the [original model card](https://huggingface.co/prince-canuma/Spark-TTS-0.5B) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-audio
+```
+
+```bash
+python -m mlx_audio.tts.generate --model mlx-community/Spark-TTS-0.5B-4-6bit --text "Describe this image."
+```

audio_tokenizer_config.yaml

@@ -0,0 +1,7 @@
+highpass_cutoff_freq: 40
+sample_rate: 16000 
+segment_duration: 2.4 # (s)
+max_val_duration: 12 # (s)
+latent_hop_length: 320
+ref_segment_duration: 6
+volume_normalize: true

config.json

@@ -0,0 +1,1589 @@
+{
+    "_attn_implementation_autoset": false,
+    "add_cross_attention": false,
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 151645,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 896,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4864,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 21,
+    "min_length": 0,
+    "model_type": "qwen2",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 14,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_key_value_heads": 2,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "model.model.embed_tokens": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.self_attn.rope": false,
+        "model.model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.input_layernorm": false,
+        "model.model.layers.0.post_attention_layernorm": false,
+        "model.model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.1.self_attn.rope": false,
+        "model.model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.1.input_layernorm": false,
+        "model.model.layers.1.post_attention_layernorm": false,
+        "model.model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.2.self_attn.rope": false,
+        "model.model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.2.input_layernorm": false,
+        "model.model.layers.2.post_attention_layernorm": false,
+        "model.model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.self_attn.rope": false,
+        "model.model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.input_layernorm": false,
+        "model.model.layers.3.post_attention_layernorm": false,
+        "model.model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.self_attn.rope": false,
+        "model.model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.input_layernorm": false,
+        "model.model.layers.4.post_attention_layernorm": false,
+        "model.model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.5.self_attn.rope": false,
+        "model.model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.5.input_layernorm": false,
+        "model.model.layers.5.post_attention_layernorm": false,
+        "model.model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.self_attn.rope": false,
+        "model.model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.input_layernorm": false,
+        "model.model.layers.6.post_attention_layernorm": false,
+        "model.model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.self_attn.rope": false,
+        "model.model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.input_layernorm": false,
+        "model.model.layers.7.post_attention_layernorm": false,
+        "model.model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.8.self_attn.rope": false,
+        "model.model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.8.input_layernorm": false,
+        "model.model.layers.8.post_attention_layernorm": false,
+        "model.model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.self_attn.rope": false,
+        "model.model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.input_layernorm": false,
+        "model.model.layers.9.post_attention_layernorm": false,
+        "model.model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.self_attn.rope": false,
+        "model.model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.input_layernorm": false,
+        "model.model.layers.10.post_attention_layernorm": false,
+        "model.model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.11.self_attn.rope": false,
+        "model.model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.11.input_layernorm": false,
+        "model.model.layers.11.post_attention_layernorm": false,
+        "model.model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.self_attn.rope": false,
+        "model.model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.input_layernorm": false,
+        "model.model.layers.12.post_attention_layernorm": false,
+        "model.model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.self_attn.rope": false,
+        "model.model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.input_layernorm": false,
+        "model.model.layers.13.post_attention_layernorm": false,
+        "model.model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.14.self_attn.rope": false,
+        "model.model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.14.input_layernorm": false,
+        "model.model.layers.14.post_attention_layernorm": false,
+        "model.model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.self_attn.rope": false,
+        "model.model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.input_layernorm": false,
+        "model.model.layers.15.post_attention_layernorm": false,
+        "model.model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.self_attn.rope": false,
+        "model.model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.input_layernorm": false,
+        "model.model.layers.16.post_attention_layernorm": false,
+        "model.model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.17.self_attn.rope": false,
+        "model.model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.17.input_layernorm": false,
+        "model.model.layers.17.post_attention_layernorm": false,
+        "model.model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.self_attn.rope": false,
+        "model.model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.input_layernorm": false,
+        "model.model.layers.18.post_attention_layernorm": false,
+        "model.model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.self_attn.rope": false,
+        "model.model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.input_layernorm": false,
+        "model.model.layers.19.post_attention_layernorm": false,
+        "model.model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.20.self_attn.rope": false,
+        "model.model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.20.input_layernorm": false,
+        "model.model.layers.20.post_attention_layernorm": false,
+        "model.model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.21.self_attn.rope": false,
+        "model.model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.21.input_layernorm": false,
+        "model.model.layers.21.post_attention_layernorm": false,
+        "model.model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.22.self_attn.rope": false,
+        "model.model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.22.input_layernorm": false,
+        "model.model.layers.22.post_attention_layernorm": false,
+        "model.model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.23.self_attn.rope": false,
+        "model.model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.23.input_layernorm": false,
+        "model.model.layers.23.post_attention_layernorm": false,
+        "model.model.norm": false
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "model.model.embed_tokens": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.0.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.self_attn.rope": false,
+        "model.model.layers.0.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.0.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.0.input_layernorm": false,
+        "model.model.layers.0.post_attention_layernorm": false,
+        "model.model.layers.1.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.1.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.1.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.1.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.1.self_attn.rope": false,
+        "model.model.layers.1.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.1.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.1.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.1.input_layernorm": false,
+        "model.model.layers.1.post_attention_layernorm": false,
+        "model.model.layers.2.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.2.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.2.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.2.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.2.self_attn.rope": false,
+        "model.model.layers.2.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.2.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.2.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.2.input_layernorm": false,
+        "model.model.layers.2.post_attention_layernorm": false,
+        "model.model.layers.3.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.self_attn.rope": false,
+        "model.model.layers.3.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.3.input_layernorm": false,
+        "model.model.layers.3.post_attention_layernorm": false,
+        "model.model.layers.4.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.self_attn.rope": false,
+        "model.model.layers.4.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.4.input_layernorm": false,
+        "model.model.layers.4.post_attention_layernorm": false,
+        "model.model.layers.5.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.5.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.5.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.5.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.5.self_attn.rope": false,
+        "model.model.layers.5.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.5.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.5.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.5.input_layernorm": false,
+        "model.model.layers.5.post_attention_layernorm": false,
+        "model.model.layers.6.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.self_attn.rope": false,
+        "model.model.layers.6.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.6.input_layernorm": false,
+        "model.model.layers.6.post_attention_layernorm": false,
+        "model.model.layers.7.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.self_attn.rope": false,
+        "model.model.layers.7.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.7.input_layernorm": false,
+        "model.model.layers.7.post_attention_layernorm": false,
+        "model.model.layers.8.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.8.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.8.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.8.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.8.self_attn.rope": false,
+        "model.model.layers.8.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.8.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.8.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.8.input_layernorm": false,
+        "model.model.layers.8.post_attention_layernorm": false,
+        "model.model.layers.9.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.self_attn.rope": false,
+        "model.model.layers.9.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.9.input_layernorm": false,
+        "model.model.layers.9.post_attention_layernorm": false,
+        "model.model.layers.10.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.self_attn.rope": false,
+        "model.model.layers.10.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.10.input_layernorm": false,
+        "model.model.layers.10.post_attention_layernorm": false,
+        "model.model.layers.11.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.11.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.11.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.11.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.11.self_attn.rope": false,
+        "model.model.layers.11.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.11.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.11.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.11.input_layernorm": false,
+        "model.model.layers.11.post_attention_layernorm": false,
+        "model.model.layers.12.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.self_attn.rope": false,
+        "model.model.layers.12.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.12.input_layernorm": false,
+        "model.model.layers.12.post_attention_layernorm": false,
+        "model.model.layers.13.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.self_attn.rope": false,
+        "model.model.layers.13.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.13.input_layernorm": false,
+        "model.model.layers.13.post_attention_layernorm": false,
+        "model.model.layers.14.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.14.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.14.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.14.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.14.self_attn.rope": false,
+        "model.model.layers.14.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.14.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.14.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.14.input_layernorm": false,
+        "model.model.layers.14.post_attention_layernorm": false,
+        "model.model.layers.15.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.self_attn.rope": false,
+        "model.model.layers.15.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.15.input_layernorm": false,
+        "model.model.layers.15.post_attention_layernorm": false,
+        "model.model.layers.16.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.self_attn.rope": false,
+        "model.model.layers.16.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.16.input_layernorm": false,
+        "model.model.layers.16.post_attention_layernorm": false,
+        "model.model.layers.17.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.17.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.17.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.17.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.17.self_attn.rope": false,
+        "model.model.layers.17.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.17.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.17.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.17.input_layernorm": false,
+        "model.model.layers.17.post_attention_layernorm": false,
+        "model.model.layers.18.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.self_attn.rope": false,
+        "model.model.layers.18.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.18.input_layernorm": false,
+        "model.model.layers.18.post_attention_layernorm": false,
+        "model.model.layers.19.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.self_attn.rope": false,
+        "model.model.layers.19.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.19.input_layernorm": false,
+        "model.model.layers.19.post_attention_layernorm": false,
+        "model.model.layers.20.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.20.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.20.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.20.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.20.self_attn.rope": false,
+        "model.model.layers.20.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.20.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.20.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.20.input_layernorm": false,
+        "model.model.layers.20.post_attention_layernorm": false,
+        "model.model.layers.21.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.21.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.21.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.21.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.21.self_attn.rope": false,
+        "model.model.layers.21.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.21.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.21.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.21.input_layernorm": false,
+        "model.model.layers.21.post_attention_layernorm": false,
+        "model.model.layers.22.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.22.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.22.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.22.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.22.self_attn.rope": false,
+        "model.model.layers.22.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.22.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.22.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.22.input_layernorm": false,
+        "model.model.layers.22.post_attention_layernorm": false,
+        "model.model.layers.23.self_attn.q_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.23.self_attn.k_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.23.self_attn.v_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.23.self_attn.o_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.23.self_attn.rope": false,
+        "model.model.layers.23.mlp.gate_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.23.mlp.down_proj": {
+            "group_size": 64,
+            "bits": 6
+        },
+        "model.model.layers.23.mlp.up_proj": {
+            "group_size": 64,
+            "bits": 4
+        },
+        "model.model.layers.23.input_layernorm": false,
+        "model.model.layers.23.post_attention_layernorm": false,
+        "model.model.norm": false
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "sep_token_id": null,
+    "sliding_window": 32768,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "transformers_version": "4.51.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 166000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fbd9cbb7ecccfef12416030883033439433e77d84e9d0e06d9d4d9d0b4e594
+size 298572047

model.safetensors.index.json

@@ -0,0 +1,635 @@
+{
+    "metadata": {
+        "total_size": 298503040
+    },
+    "weight_map": {
+        "model.embed_tokens.biases": "model.safetensors",
+        "model.embed_tokens.scales": "model.safetensors",
+        "model.embed_tokens.weight": "model.safetensors",
+        "model.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.10.input_layernorm.weight": "model.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.11.input_layernorm.weight": "model.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.12.input_layernorm.weight": "model.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.13.input_layernorm.weight": "model.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.14.input_layernorm.weight": "model.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.15.input_layernorm.weight": "model.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.16.input_layernorm.weight": "model.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.17.input_layernorm.weight": "model.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.18.input_layernorm.weight": "model.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.19.input_layernorm.weight": "model.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.20.input_layernorm.weight": "model.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.21.input_layernorm.weight": "model.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.22.input_layernorm.weight": "model.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.23.input_layernorm.weight": "model.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.8.input_layernorm.weight": "model.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.9.input_layernorm.weight": "model.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "model.norm.weight": "model.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8b057d6ca205a429cc3428b9fc815f0d6ee1d53106dd5e5b129ef9db2ff057
+size 14129172

wav2vec2-large-xlsr-53/config.json

@@ -0,0 +1,83 @@
+{
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForPreTraining"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "transformers_version": "4.7.0.dev0",
+  "vocab_size": 32
+}

wav2vec2-large-xlsr-53/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8b60ccc08ffcd555abc1df8e113228b9956e855034f4287d8c4ab7ae8b53ba
+size 1261803488

wav2vec2-large-xlsr-53/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}