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

README.md

@@ -0,0 +1,50 @@
+---
+base_model:
+- google/gemma-3-4b-pt
+- google/gemma-3-4b-it
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# gemma-3-4b-pt-InitializedEmbeds
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [Linear](https://arxiv.org/abs/2203.05482) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [google/gemma-3-4b-pt](https://huggingface.co/google/gemma-3-4b-pt)
+* [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+merge_method: linear
+dtype: bfloat16
+models:
+  - model: google/gemma-3-4b-pt
+    parameters:
+      weight: 1.0
+  - model: google/gemma-3-4b-it
+    parameters:
+      weight: 0.0
+tokenizer:
+  source: google/gemma-3-4b-it
+  tokens:
+    <start_of_turn>:
+      source: google/gemma-3-4b-it
+      force: true
+    <end_of_turn>:
+      source: google/gemma-3-4b-it
+      force: true
+
+```

added_tokens.json

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

chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

config.json

@@ -0,0 +1,56 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 34,
+    "num_key_value_heads": 4,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000.0,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "use_cache": true,
+    "vocab_size": 262145
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "vision_use_head": false
+  }
+}

mergekit_config.yml

@@ -0,0 +1,18 @@
+merge_method: linear
+dtype: bfloat16
+models:
+  - model: google/gemma-3-4b-pt
+    parameters:
+      weight: 1.0
+  - model: google/gemma-3-4b-it
+    parameters:
+      weight: 0.0
+tokenizer:
+  source: google/gemma-3-4b-it
+  tokens:
+    <start_of_turn>:
+      source: google/gemma-3-4b-it
+      force: true
+    <end_of_turn>:
+      source: google/gemma-3-4b-it
+      force: true

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d653a586d788e89ea29d2f1222c7fe1cb3ad9dcb9d02c302fc7c3b880e803b
+size 4981187776

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e92dfce17ca3ee2cbc6306c79eb3017e2de2775d78c92e84ccfe1475b356c3
+size 3618767576

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"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-00001-of-00002.safetensors", "language_model.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00001-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-00001-of-00002.safetensors", "language_model.model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", "language_model.model.layers.26.mlp.down_proj.weight": "model-00001-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-00002-of-00002.safetensors", "language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-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-00002-of-00002.safetensors", "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "language_model.model.norm.weight": "model-00002-of-00002.safetensors", "multi_modal_projector.mm_input_projection_weight": "model-00002-of-00002.safetensors", "multi_modal_projector.mm_soft_emb_norm.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors", "vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors"}}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

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:f24b3f0a35502067d40ae927a43d38bb295902b3d1f6ebcafe413dea73f15f7f
+size 33384568

tokenizer.model

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