Add Starlight-Flash bf16 weights

.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 +1,18 @@
+---
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+  - qwen3_5
+---
+
+# Starlight-Flash
+
+Qwen3.5 text causal LM (`Qwen3_5ForCausalLM`).
+
+- 32 layers, hidden size 4096, intermediate size 12288
+- vocab 248320
+- dtype bf16
+- context 262144
+- four safetensor shards
+
+GGUF is a separate repo: [Sethblocks/Starlight-Flash-GGUF](https://huggingface.co/Sethblocks/Starlight-Flash-GGUF) (`Starlight-Flash-9.2B-Q8_0.gguf`).

chat_template.jinja

@@ -0,0 +1,155 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- generation -%}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {# {%- set content = content.split('</think>')[-1].lstrip('\n') %} #}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {# {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }} #}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+        {% endgeneration %}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,83 @@
+{
+  "architectures": [
+    "Qwen3_5ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_output_gate": true,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 248044,
+  "full_attention_interval": 4,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention",
+    "linear_attention",
+    "linear_attention",
+    "linear_attention",
+    "full_attention"
+  ],
+  "linear_conv_kernel_dim": 4,
+  "linear_key_head_dim": 128,
+  "linear_num_key_heads": 16,
+  "linear_num_value_heads": 32,
+  "linear_value_head_dim": 128,
+  "mamba_ssm_dtype": "float32",
+  "max_position_embeddings": 262144,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_5_text",
+  "mtp_num_hidden_layers": 1,
+  "mtp_use_dedicated_embeddings": false,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "pad_token_id": null,
+  "partial_rotary_factor": 0.25,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "mrope_interleaved": true,
+    "mrope_section": [
+      11,
+      11,
+      10
+    ],
+    "partial_rotary_factor": 0.25,
+    "rope_theta": 10000000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.4",
+  "use_cache": true,
+  "vocab_size": 248320
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 248044,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.5.4",
+  "use_cache": true
+}

model-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c5240cb9d186477196222d52eaba4ec763f5c38905925212f7630f9527f9ea
+size 5075109232

model-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39348491458cb94b17e074d063a7dae496806ee8575a55aa83b1ed4ab0124508
+size 5033170560

model-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071349adb41afc9ca1e17375c7585dde287b956e6a53aa317cb61fe8a6c7beb1
+size 5066725760

model-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a5f8f13e8ddea34331d689aeae77c2c26053d2c30e1f4a56a450265aaced87
+size 3219233256

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {}, "weight_map": {"lm_head.weight": "model-00001.safetensors", "model.embed_tokens.weight": "model-00001.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002.safetensors", "mtp.layers.0.mlp.down_proj.weight": "model-00002.safetensors", "mtp.layers.0.mlp.gate_proj.weight": "model-00002.safetensors", "mtp.layers.0.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003.safetensors", "model.layers.14.linear_attn.in_proj_qkv.weight": "model-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003.safetensors", "model.layers.26.linear_attn.in_proj_qkv.weight": "model-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003.safetensors", "model.layers.30.linear_attn.in_proj_qkv.weight": "model-00003.safetensors", "model.layers.9.linear_attn.in_proj_qkv.weight": "model-00003.safetensors", "mtp.fc.weight": "model-00003.safetensors", "mtp.layers.0.self_attn.q_proj.weight": "model-00003.safetensors", "model.layers.10.linear_attn.in_proj_qkv.weight": "model-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003.safetensors", "model.layers.0.linear_attn.in_proj_qkv.weight": "model-00003.safetensors", "model.layers.1.linear_attn.in_proj_qkv.weight": "model-00003.safetensors", "model.layers.22.linear_attn.in_proj_qkv.weight": "model-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003.safetensors", "model.layers.8.linear_attn.in_proj_qkv.weight": "model-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004.safetensors", "model.layers.4.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.16.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.17.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.18.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004.safetensors", "model.layers.2.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.24.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.25.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.5.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.6.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.20.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.21.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.12.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.13.linear_attn.in_proj_qkv.weight": "model-00004.safetensors", "model.layers.14.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.14.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004.safetensors", "model.layers.26.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.26.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004.safetensors", "model.layers.30.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.30.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.9.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.9.linear_attn.out_proj.weight": "model-00004.safetensors", "mtp.layers.0.self_attn.o_proj.weight": "model-00004.safetensors", "model.layers.10.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.10.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004.safetensors", "model.layers.0.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.0.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.1.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.1.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.21.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.22.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.22.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004.safetensors", "model.layers.8.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.8.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004.safetensors", "model.layers.4.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.4.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.16.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.16.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.17.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.17.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.18.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.18.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004.safetensors", "model.layers.2.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.24.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.24.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.25.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.25.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.5.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.5.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.6.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.6.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.2.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.20.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.20.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.21.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.28.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.28.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.29.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.29.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.12.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.12.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.13.linear_attn.in_proj_z.weight": "model-00004.safetensors", "model.layers.13.linear_attn.out_proj.weight": "model-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004.safetensors", "mtp.layers.0.self_attn.k_proj.weight": "model-00004.safetensors", "mtp.layers.0.self_attn.v_proj.weight": "model-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004.safetensors", "model.layers.14.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.14.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.26.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.26.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.30.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.30.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.10.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.10.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.0.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.0.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.1.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.1.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.22.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.22.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.8.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.8.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.9.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.9.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.4.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.4.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.16.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.16.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.17.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.17.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.18.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.18.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.2.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.2.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.24.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.24.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.25.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.25.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.5.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.5.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.6.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.6.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.20.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.20.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.21.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.21.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.28.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.28.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.29.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.29.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.12.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.12.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.13.linear_attn.in_proj_b.weight": "model-00004.safetensors", "model.layers.13.linear_attn.in_proj_a.weight": "model-00004.safetensors", "model.layers.14.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.16.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.26.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.30.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.10.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.0.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.1.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.22.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.8.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.9.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.4.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.5.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.17.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.18.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.2.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.24.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.25.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.6.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.20.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.21.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.28.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.29.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.12.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.13.linear_attn.conv1d.weight": "model-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004.safetensors", "mtp.layers.0.input_layernorm.weight": "model-00004.safetensors", "mtp.layers.0.post_attention_layernorm.weight": "model-00004.safetensors", "mtp.norm.weight": "model-00004.safetensors", "mtp.pre_fc_norm_embedding.weight": "model-00004.safetensors", "mtp.pre_fc_norm_hidden.weight": "model-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004.safetensors", "model.norm.weight": "model-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004.safetensors", "model.layers.14.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.15.self_attn.k_norm.weight": "model-00004.safetensors", "model.layers.15.self_attn.q_norm.weight": "model-00004.safetensors", "model.layers.26.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.27.self_attn.k_norm.weight": "model-00004.safetensors", "model.layers.27.self_attn.q_norm.weight": "model-00004.safetensors", "model.layers.3.self_attn.k_norm.weight": "model-00004.safetensors", "model.layers.3.self_attn.q_norm.weight": "model-00004.safetensors", "model.layers.30.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.9.linear_attn.norm.weight": "model-00004.safetensors", "mtp.layers.0.self_attn.k_norm.weight": "model-00004.safetensors", "mtp.layers.0.self_attn.q_norm.weight": "model-00004.safetensors", "model.layers.10.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.11.self_attn.k_norm.weight": "model-00004.safetensors", "model.layers.11.self_attn.q_norm.weight": "model-00004.safetensors", "model.layers.0.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.1.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.22.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.23.self_attn.k_norm.weight": "model-00004.safetensors", "model.layers.7.self_attn.k_norm.weight": "model-00004.safetensors", "model.layers.7.self_attn.q_norm.weight": "model-00004.safetensors", "model.layers.8.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.31.self_attn.k_norm.weight": "model-00004.safetensors", "model.layers.31.self_attn.q_norm.weight": "model-00004.safetensors", "model.layers.4.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.16.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.17.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.18.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.19.self_attn.k_norm.weight": "model-00004.safetensors", "model.layers.19.self_attn.q_norm.weight": "model-00004.safetensors", "model.layers.2.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.23.self_attn.q_norm.weight": "model-00004.safetensors", "model.layers.24.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.25.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.5.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.6.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.20.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.21.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.28.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.29.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.12.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.13.linear_attn.norm.weight": "model-00004.safetensors", "model.layers.16.linear_attn.A_log": "model-00004.safetensors", "model.layers.26.linear_attn.A_log": "model-00004.safetensors", "model.layers.28.linear_attn.A_log": "model-00004.safetensors", "model.layers.30.linear_attn.A_log": "model-00004.safetensors", "model.layers.10.linear_attn.A_log": "model-00004.safetensors", "model.layers.12.linear_attn.A_log": "model-00004.safetensors", "model.layers.0.linear_attn.A_log": "model-00004.safetensors", "model.layers.1.linear_attn.A_log": "model-00004.safetensors", "model.layers.22.linear_attn.A_log": "model-00004.safetensors", "model.layers.8.linear_attn.A_log": "model-00004.safetensors", "model.layers.9.linear_attn.A_log": "model-00004.safetensors", "model.layers.4.linear_attn.A_log": "model-00004.safetensors", "model.layers.5.linear_attn.A_log": "model-00004.safetensors", "model.layers.17.linear_attn.A_log": "model-00004.safetensors", "model.layers.18.linear_attn.A_log": "model-00004.safetensors", "model.layers.2.linear_attn.A_log": "model-00004.safetensors", "model.layers.24.linear_attn.A_log": "model-00004.safetensors", "model.layers.25.linear_attn.A_log": "model-00004.safetensors", "model.layers.6.linear_attn.A_log": "model-00004.safetensors", "model.layers.20.linear_attn.A_log": "model-00004.safetensors", "model.layers.21.linear_attn.A_log": "model-00004.safetensors", "model.layers.29.linear_attn.A_log": "model-00004.safetensors", "model.layers.13.linear_attn.A_log": "model-00004.safetensors", "model.layers.14.linear_attn.A_log": "model-00004.safetensors", "model.layers.14.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.16.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.26.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.30.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.10.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.0.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.1.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.22.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.8.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.9.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.4.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.5.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.17.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.18.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.2.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.24.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.25.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.6.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.20.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.21.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.28.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.29.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.12.linear_attn.dt_bias": "model-00004.safetensors", "model.layers.13.linear_attn.dt_bias": "model-00004.safetensors"}}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}