Add files using upload-large-folder tool

.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

README.md

@@ -0,0 +1,41 @@
+---
+license: gemma
+library_name: transformers
+pipeline_tag: image-text-to-text
+extra_gated_heading: Access Gemma on Hugging Face
+extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
+  agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
+  Face and click below. Requests are processed immediately.
+extra_gated_button_content: Acknowledge license
+base_model: google/gemma-3-4b-it
+tags:
+- mlx
+---
+
+# alexgusevski/gemma-3-text-4b-it-fp16-mlx
+
+The Model [alexgusevski/gemma-3-text-4b-it-fp16-mlx](https://huggingface.co/alexgusevski/gemma-3-text-4b-it-fp16-mlx) was
+converted to MLX format from [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it)
+using mlx-lm version **0.22.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("alexgusevski/gemma-3-text-4b-it-fp16-mlx")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

config.json

@@ -0,0 +1,31 @@
+{
+    "architectures": [
+        "Gemma3ForConditionalGeneration"
+    ],
+    "boi_token_index": 255999,
+    "eoi_token_index": 256000,
+    "eos_token_id": [
+        1,
+        106
+    ],
+    "image_token_index": 262144,
+    "initializer_range": 0.02,
+    "mm_tokens_per_image": 256,
+    "model_type": "gemma3",
+    "text_config": {
+        "hidden_size": 2560,
+        "intermediate_size": 10240,
+        "model_type": "gemma3_text",
+        "num_hidden_layers": 34,
+        "rope_scaling": {
+            "factor": 8.0,
+            "rope_type": "linear"
+        },
+        "sliding_window": 1024,
+        "vocab_size": 262208,
+        "num_attention_heads": 8,
+        "num_key_value_heads": 4
+    },
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.50.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a38f837c7e9f463d2997231ba2b07d2c82b63a7925c3bd8f30ba7a68021765
+size 5338068786

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05cc0147801ce2a028c7294fa8cf4149a563ce8414685db158e6ff7acefb746
+size 3765020765

model.safetensors.index.json

@@ -0,0 +1,452 @@
+{
+    "metadata": {
+        "total_size": 9103031296
+    },
+    "weight_map": {
+        "language_model.lm_head.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "language_model.model.norm.weight": "model-00002-of-00002.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074