Training in progress, step 200

.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 +1,59 @@
+---
+base_model: igorktech/gemma-3n-E2B-it-language
+library_name: transformers
+model_name: Custom3
+tags:
+- generated_from_trainer
+- unsloth
+- sft
+- trl
+licence: license
+---
+
+# Model Card for Custom3
+
+This model is a fine-tuned version of [igorktech/gemma-3n-E2B-it-language](https://huggingface.co/igorktech/gemma-3n-E2B-it-language).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="igorktech/Custom3", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/igorktech01/huggingface/runs/bih359ta) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.21.0
+- Transformers: 4.55.0
+- Pytorch: 2.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "igorktech/gemma-3n-E2B-it-language",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2)))",
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6553295eb0b78ca6a1edbc1fea1179d462539d5023a8bc15c72149928f8b07f4
+size 169139064

chat_template.jinja

@@ -0,0 +1,125 @@
+{{ 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 -%}
+
+{# Inject tools definitions here if available #}
+{%- if tools -%}
+  {#– Serialize all tools into one JSON blob, separated by newlines –#}
+  {%- set tools_json = tools | map('tojson') | join('
+') -%}
+  {#– Append the entire block to first_user_prefix in one go –#}
+  {%- set first_user_prefix = first_user_prefix
+       ~ "# Tools
+
+"
+       ~ "You may call one or more functions to assist with the user query.
+
+"
+       ~ "You are provided with function signatures within `<tools>` XML tags:
+"
+       ~ "<tools>
+"
+       ~ tools_json
+       ~ "
+</tools>
+
+"
+       ~ "For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+"
+       ~ "<tool_call>
+"
+       ~ '{"name": <function-name>, "arguments": <args-json-object>}'
+       ~ "
+</tool_call>
+
+"
+  -%}
+{%- endif -%}
+
+{# Identify where to insert optional tool segments #}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=loop_messages|length - 1) -%}
+{%- for msg in loop_messages[::-1] -%}
+    {%- set idx = (loop_messages|length - 1) - loop.index0 -%}
+    {%- if ns.multi_step_tool and msg['role']=='user' and msg['content'] is string and not (msg['content'].startswith('<tool_response>') and msg['content'].endswith('</tool_response>')) -%}
+        {%- set ns.multi_step_tool = false -%}
+        {%- set ns.last_query_index = idx -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{# Render each message turn #}
+{%- for message in loop_messages -%}
+  {%- set role = "model" if message.role == 'assistant' else message.role -%}
+  {{ '<start_of_turn>' ~ role ~ "
+" ~ (first_user_prefix if loop.first else "") -}}
+  {%- if message.content is string -%}
+    {%- set content = message.content -%}
+  {%- elif message.content is iterable -%}
+    {%- set content = '' -%}
+    {%- for item in message.content -%}
+      {%- if item.type == 'text' -%}
+        {%- set content = content + item.text -%}
+      {%- elif item.type == 'image' -%}
+        {%- set content = content + '<image_soft_token>' -%}
+      {%- elif item.type == 'audio' -%}
+        {%- set content = content + '<audio_soft_token>' -%}
+      {%- endif -%}
+    {%- endfor -%}
+  {%- else -%}
+    {{ raise_exception("Invalid content type: " ~ message.role) }}
+  {%- endif -%}
+
+  {# Render by role #}
+  {%- if message.role == 'tool' -%}
+    {{ '<tool_response>
+' + content + '
+</tool_response>' }}
+  {%- elif message.role == 'assistant' -%}
+    {{ content }}
+    {# Append any tool_calls #}
+    {%- if message.tool_calls -%}
+      {%- for tool_call in message.tool_calls -%}
+        {%- if (loop.first and content) or (not loop.first) -%}
+            {{- '
+' }}
+        {%- endif -%}
+        {%- if tool_call.function -%}
+            {%- set tool_call = tool_call.function -%}
+        {%- endif -%}
+        {{- '<tool_call>
+{"name": "' }}
+        {{- tool_call.name }}
+        {{- '", "arguments": ' }}
+        {%- if tool_call.arguments is string -%}
+            {{- tool_call.arguments }}
+        {%- else -%}
+            {{- tool_call.arguments | tojson }}
+        {%- endif -%}
+        {{- '}
+</tool_call>' }}
+      {%- endfor -%}
+    {%- endif -%}
+  {%- else -%}
+    {{ content }}
+  {%- endif -%}
+  {{ '<end_of_turn>
+' }}
+
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

config.json

@@ -0,0 +1,107 @@
+{
+  "activation_sparsity_pattern": [
+    0.95,
+    0.95,
+    0.95,
+    0.95,
+    0.95,
+    0.95,
+    0.95,
+    0.95,
+    0.95,
+    0.95,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0,
+    0.0
+  ],
+  "altup_active_idx": 0,
+  "altup_coef_clip": 120.0,
+  "altup_correct_scale": true,
+  "altup_num_inputs": 4,
+  "architectures": [
+    "Gemma3nForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2048,
+  "hidden_size_per_layer_input": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": [
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192,
+    8192
+  ],
+  "laurel_rank": 64,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3n_text",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 21,
+  "num_key_value_heads": 2,
+  "num_kv_shared_layers": 10,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 512,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "unsloth_version": "2025.8.1",
+  "use_cache": true,
+  "vocab_size": 262400,
+  "vocab_size_per_layer_input": 262144
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d24c65abac4b9c97ccf90eb9c2d75053973353c591576a444d41c7bc0947d99b
+size 3685299792

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac4b8d38c16e1548dd38e22fea6af818baaaaccb5ec6792bd4f69dd0638aa95
+size 2890925736

model.safetensors.index.json

@@ -0,0 +1,523 @@
+{
+  "metadata": {
+    "total_parameters": 3288078736,
+    "total_size": 6576157472
+  },
+  "weight_map": {
+    "model.language_model.altup_projections.0.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.altup_projections.1.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.altup_projections.2.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.altup_unembed_projections.0.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.altup_unembed_projections.1.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.altup_unembed_projections.2.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.embed_tokens_per_layer.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.0.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.altup.correct_output_scale": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.altup.correction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.altup.modality_router.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.altup.prediction_coefs.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.altup.router_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.laurel.linear_left.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.laurel.linear_right.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.laurel.post_laurel_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.per_layer_input_gate.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.per_layer_projection.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.post_per_layer_input_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.per_layer_model.language_model_projection.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.per_layer_projection_norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "audio_token": "<audio_soft_token>",
+  "boa_token": "<start_of_audio>",
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoa_token": "<end_of_audio>",
+  "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:b6c35ee648c07754b44cd9e371c75d4caa05c4504910b7ad29b1847ee9d8ba5d
+size 33442553

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1782413fe24dc6c88ce6e4056b4cf9ece4351df907eb2df4e50a02a331f2e87
+size 5816