Add files using upload-large-folder tool

.gitattributes

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

README.md

@@ -0,0 +1,45 @@
+---
+license: gemma
+datasets:
+- NbAiLab/aurora-sft-2512-filtered
+language:
+- 'no'
+- nb
+- nn
+base_model: NbAiLab/borealis-4b-instruct-preview
+pipeline_tag: text-generation
+library_name: mlx
+tags:
+- conversational
+- instruct
+- experimental
+- mlx
+---
+
+# NbAiLab/borealis-4b-instruct-preview-mlx
+
+This model [NbAiLab/borealis-4b-instruct-preview-mlx](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview-mlx) was
+converted to MLX format from [NbAiLab/borealis-4b-instruct-preview](https://huggingface.co/NbAiLab/borealis-4b-instruct-preview)
+using mlx-lm version **0.29.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("NbAiLab/borealis-4b-instruct-preview-mlx")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

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 +1,84 @@
+{
+    "architectures": [
+        "Gemma3ForConditionalGeneration"
+    ],
+    "boi_token_index": 255999,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "eoi_token_index": 256000,
+    "eos_token_id": 106,
+    "hidden_size": 2560,
+    "image_token_index": 262144,
+    "initializer_range": 0.02,
+    "mm_tokens_per_image": 256,
+    "model_type": "gemma3",
+    "pad_token_id": 0,
+    "text_config": {
+        "_sliding_window_pattern": 6,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_logit_softcapping": null,
+        "dtype": "bfloat16",
+        "final_logit_softcapping": null,
+        "head_dim": 256,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 2560,
+        "initializer_range": 0.02,
+        "intermediate_size": 10240,
+        "layer_types": [
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention"
+        ],
+        "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,
+        "use_bidirectional_attention": false,
+        "use_cache": false,
+        "vocab_size": 262208
+    },
+    "transformers_version": "4.57.1",
+    "use_cache": false
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    106,
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d17dbae4be32fdb2f73c082f9743a885586c2d8223a99126982bb410f0971fe
+size 5359191915

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17bc2b87854b070f6aa436b71cde654c45d8087f4653d5af1f1d7d23dda6189
+size 5316908743

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba63fdc5facfbae0327edec0d2ba4bc2e6fa4535b84a893a9ee0555fe5f97e4c
+size 4845009801

model.safetensors.index.json

@@ -0,0 +1,452 @@
+{
+    "metadata": {
+        "total_size": 15521052672,
+        "total_parameters": 3880263168
+    },
+    "weight_map": {
+        "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.7.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.7.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "language_model.model.norm.weight": "model-00003-of-00003.safetensors"
+    }
+}

special_tokens_map.json

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

tokenizer.json

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