Update MLX weights and patched config

README.md

@@ -1,18 +1,7 @@
----
-library_name: mlx-audio
-license: apache-2.0
-pipeline_tag: text-to-speech
-tags:
-- mlx
-- text-to-speech
-- speech
-- speech generation
-- voice cloning
-- tts
----
-
 # mlx-community/Soprano-80M-bf16
-This model was converted to MLX format from [`ekwek/Soprano-80M`](https://huggingface.co/ekwek/Soprano-80M) using mlx-audio version **0.2.10**.
+
+This model was converted to MLX format from [`ekwek/Soprano-80M`](https://huggingface.co/ekwek/Soprano-80M) using mlx-audio version **0.3.1**.
+
 Refer to the [original model card](https://huggingface.co/ekwek/Soprano-80M) for more details on the model.
 
 ## Use with mlx-audio
@@ -23,16 +12,20 @@ pip install -U mlx-audio
 
 ### CLI Example:
 ```bash
-    python -m mlx_audio.tts.generate --model mlx-community/Soprano-80M-bf16 --text "Hello, this is a test."
+python -m mlx_audio.tts.generate --model mlx-community/Soprano-80M-bf16 --text "Hello, this is a test."
 ```
+
 ### Python Example:
-```python
-    from mlx_audio.tts.utils import load_model
-    from mlx_audio.tts.generate import generate_audio
-    model = load_model("mlx-community/Soprano-80M-bf16")
-    generate_audio(
-        model=model, text="Hello, this is a test.",
-        file_prefix="test_audio",
-    )
+```python        
+from mlx_audio.tts.utils import load_model
+from mlx_audio.tts.generate import generate_audio
+
+model = load_model("mlx-community/Soprano-80M-bf16")
+generate_audio(
+    model=model,
+    text="Hello, this is a test.",
+    ref_audio="path_to_audio.wav",
+    file_prefix="test_audio",
+)
 
 ```

config.json

@@ -1,31 +1,49 @@
 {
-  "architectures": [
-    "SopranoForCausalLM"
-  ],
-  "model_type": "soprano",
-  "hidden_size": 512,
-  "num_hidden_layers": 17,
-  "num_attention_heads": 4,
-  "num_key_value_heads": 1,
-  "head_dim": 128,
-  "intermediate_size": 2304,
-  "vocab_size": 8192,
-  "max_position_embeddings": 512,
-  "rms_norm_eps": 1e-06,
-  "rope_theta": 10000,
-  "tie_word_embeddings": false,
-  "decoder_num_layers": 8,
-  "decoder_dim": 512,
-  "decoder_intermediate_dim": 1536,
-  "hop_length": 512,
-  "n_fft": 2048,
-  "upscale": 4,
-  "dw_kernel": 3,
-  "sample_rate": 32000,
-  "token_size": 2048,
-  "receptive_field": 4,
-  "use_cache": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "pad_token_id": 0
+    "architectures": [
+        "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 3,
+    "dtype": "bfloat16",
+    "eos_token_id": 3,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 512,
+    "initializer_range": 0.041666666666666664,
+    "intermediate_size": 2304,
+    "layer_types": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 512,
+    "max_window_layers": 17,
+    "model_type": "soprano",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 17,
+    "num_key_value_heads": 1,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 10000,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "transformers_version": "4.56.1",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 8192
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 3,
+  "eos_token_id": 3,
+  "transformers_version": "4.56.1"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e42d42bc879213d49d940e0884024eb153fb6daccf2229864cca0fbbbb268a
-size 217333883
+oid sha256:caf6e44b8a38dffaf8e3598771caaf44614b8e75a0a0d2bb38daa44b4504e132
+size 217335071

model.safetensors.index.json

@@ -84,195 +84,195 @@
         "decoder.decoder.norm.weight": "model.safetensors",
         "decoder.head.out.bias": "model.safetensors",
         "decoder.head.out.weight": "model.safetensors",
-        "language_model.embed_tokens.weight": "model.safetensors",
-        "language_model.layers.0.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.0.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.0.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.0.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.0.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.0.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.0.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.0.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.0.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.0.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.0.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.1.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.1.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.1.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.1.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.1.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.1.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.1.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.1.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.1.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.1.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.1.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.10.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.10.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.10.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.10.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.10.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.10.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.10.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.10.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.10.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.10.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.10.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.11.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.11.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.11.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.11.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.11.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.11.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.11.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.11.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.11.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.11.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.11.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.12.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.12.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.12.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.12.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.12.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.12.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.12.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.12.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.12.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.12.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.12.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.13.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.13.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.13.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.13.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.13.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.13.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.13.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.13.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.13.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.13.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.13.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.14.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.14.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.14.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.14.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.14.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.14.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.14.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.14.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.14.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.14.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.14.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.15.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.15.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.15.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.15.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.15.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.15.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.15.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.15.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.15.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.15.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.15.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.16.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.16.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.16.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.16.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.16.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.16.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.16.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.16.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.16.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.16.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.16.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.2.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.2.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.2.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.2.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.2.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.2.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.2.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.2.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.2.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.2.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.2.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.3.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.3.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.3.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.3.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.3.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.3.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.3.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.3.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.3.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.3.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.3.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.4.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.4.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.4.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.4.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.4.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.4.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.4.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.4.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.4.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.4.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.4.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.5.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.5.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.5.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.5.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.5.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.5.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.5.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.5.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.5.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.5.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.5.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.6.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.6.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.6.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.6.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.6.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.6.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.6.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.6.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.6.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.6.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.6.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.7.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.7.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.7.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.7.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.7.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.7.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.7.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.7.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.7.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.7.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.7.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.8.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.8.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.8.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.8.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.8.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.8.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.8.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.8.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.8.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.8.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.8.self_attn.v_proj.weight": "model.safetensors",
-        "language_model.layers.9.input_layernorm.weight": "model.safetensors",
-        "language_model.layers.9.mlp.down_proj.weight": "model.safetensors",
-        "language_model.layers.9.mlp.gate_proj.weight": "model.safetensors",
-        "language_model.layers.9.mlp.up_proj.weight": "model.safetensors",
-        "language_model.layers.9.post_attention_layernorm.weight": "model.safetensors",
-        "language_model.layers.9.self_attn.k_norm.weight": "model.safetensors",
-        "language_model.layers.9.self_attn.k_proj.weight": "model.safetensors",
-        "language_model.layers.9.self_attn.o_proj.weight": "model.safetensors",
-        "language_model.layers.9.self_attn.q_norm.weight": "model.safetensors",
-        "language_model.layers.9.self_attn.q_proj.weight": "model.safetensors",
-        "language_model.layers.9.self_attn.v_proj.weight": "model.safetensors",
         "language_model.lm_head.weight": "model.safetensors",
-        "language_model.norm.weight": "model.safetensors"
+        "language_model.model.embed_tokens.weight": "model.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.norm.weight": "model.safetensors"
     }
 }

special_tokens_map.json

@@ -1,9 +1,9 @@
 {
-    "pad_token": {
-      "content": "[STOP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+  "pad_token": {
+    "content": "[STOP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
   }
+}