Add complete stage2 distillation inference checkpoint step 8032

sft/qwen38-distill-step8032/README.md

@@ -0,0 +1,11 @@
+# Qwen3.8-derived student: stage 2, step 8032
+
+Complete inference checkpoint after 1,000,764,291 input tokens of top-32 forward-KL distillation. Stage 3 training is separate and is not included in this snapshot.
+
+Architecture: 48 layers, hidden size 1280, 160 experts, top-6 routing; original frozen n-gram tables included. This folder contains all indexed weights and tokenizer/config files, with no dependency on local training paths. Optimizer state is not included.
+
+This final checkpoint has not yet received a generation evaluation. The earlier step-7700 checkpoint scored 3/50 final-answer accuracy on a fixed GSM8K sample; that is not a score for this checkpoint. This is an experimental model with weak multi-step mathematical reasoning.
+
+Use a Transformers/vLLM build supporting the architecture and n-gram implementation in config.json. Local inference was tested on earlier exported checkpoints with vLLM (local environment directory vllm031); inspect your engine support before use.
+
+The weight manifest records SHA-256 checksums. Original upstream model: Qwen/Qwen3.8-Flash-Next, revision de4b8e4d43b917e7706784d8bb445c9af86a3540. Upstream license terms apply.

sft/qwen38-distill-step8032/chat_template.jinja

@@ -0,0 +1,170 @@
+{%- 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 %}
+{%- set reasoning_instructions = '' %}
+{%- if enable_thinking is undefined or enable_thinking is true %}
+    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
+    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
+        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
+    {%- endif %}
+    {%- if resolved_reasoning_effort == 'xhigh' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
+    {%- elif resolved_reasoning_effort == 'low' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_instructions %}
+        {{- reasoning_instructions + '\n\n' }}
+    {%- endif %}
+    {{- "# 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 %}
+        {%- if content %}
+            {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '')  + content + '<|im_end|>\n' }}
+        {%- elif reasoning_instructions %}
+            {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+        {%- endif %}
+    {%- elif reasoning_instructions %}
+        {{- '<|im_start|>system\n' + reasoning_instructions + '<|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 %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- 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" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\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 and tool_call.arguments != '' %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- 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 false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

sft/qwen38-distill-step8032/config.json

@@ -0,0 +1,120 @@
+{
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 248044,
+  "dtype": "bfloat16",
+  "eos_token_id": 248044,
+  "full_attention_interval": 4,
+  "hc_count": 4,
+  "hc_lowrank": 160,
+  "head_dim": 256,
+  "heads_per_ngram": 8,
+  "hidden_act": "silu",
+  "hidden_size": 1280,
+  "indexer_budget": 2048,
+  "indexer_compress_ratio": 4,
+  "indexer_head_dim": 128,
+  "indexer_kv_heads": 1,
+  "indexer_n_heads": 4,
+  "initializer_range": 0.02,
+  "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_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": 8,
+  "linear_num_value_heads": 24,
+  "linear_value_head_dim": 128,
+  "make_ngram_vocab_size_divisible_by": 128,
+  "mamba_ssm_dtype": "float32",
+  "max_position_embeddings": 262144,
+  "model_type": "qwen4_exp_text",
+  "moe_intermediate_size": 320,
+  "mtp": null,
+  "mtp_num_hidden_layers": 0,
+  "mtp_use_dedicated_embeddings": false,
+  "ngram_size": 3,
+  "ngram_vocab_size_base": 20000000,
+  "num_attention_heads": 12,
+  "num_experts": 160,
+  "num_experts_per_tok": 6,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 2,
+  "output_gate_type": "sigmoid",
+  "output_router_logits": true,
+  "pad_token_id": null,
+  "partial_rotary_factor": 0.25,
+  "ple_conv_kernel_size": 4,
+  "ple_embed_dim": 2560,
+  "ple_layer_ids": [
+    2
+  ],
+  "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"
+  },
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 320,
+  "split_ngram_parts": 128,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 248320,
+  "architectures": [
+    "Qwen4ExpForCausalLM"
+  ]
+}

sft/qwen38-distill-step8032/frozen-model-00027.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a1513adbcd066ef85ead28577f781850426e65016cb56073d1e4b78d606043
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cf8581d776c5fdf3b8ee326f49893e340b107db5f2fd23519328c37f4ef6bb0
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00029.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33d0cf164a833f1ee76f3e23559854e69401b89ddf64d6f4312fd4132fc5a6c
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70885808995d7a6787d0bf091acd6526fb66c0b5fb57c6b1ccd5c41ac5245187
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00031.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9181e54f9015000d482b8bf066a835f3a97202bb9559fd037422b7d74825fd
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00032.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a3221e8109152b97584401458ad79a98fa5c9e19a5ac6905ed54b66bb309fd
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5d0023a429720affd63daf7e5a71f36317e808739c5d462c23b3ed3a2c8e51
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00034.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c446c3af607685d6331f552c3a4a298b17df648c584c8fd04577376873806018
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00035.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c080f048828c0866816df1907532c527ccd27036688bf91483c504f1711fb9
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00036.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac8f72e51ac86dcbabd0aebef8538c4e28038eb1ffc0332dcd1a2926cc71420
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00037.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6deecd49b77e8e88423e21ae2042f0f4ff675c2eb3fbce88e526a899488613
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00038.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0020a3ae064fa7163dd9928fd86fe35d6617534695cd70cec2e15f1ad49efd06
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00039.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51b84fcd68d865e738d96d006d1873b6f5efa425101ce33915fc34520763a19
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00040.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c92f45a0d9e33b42dec46f841df836569e20f155603ef112ecf18b9bf8ac2f
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00041.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d913c6dad5f6768ab5ef48dfbb38586dc66fa75424b401ec6e604a266b6403
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2be4b40cbdf6264ead8820bc41f7b241d9984ab3d958285bfd2602126f87481b
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00043.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87559f1aee2cd4d5d4e910de516b5a62ef529292ff02f0148a5dd08cff73ffc6
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66a4b6467f4234c99066c30f170da70803cd3be3502ffd08dff156a1590ef47e
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6e54fe2ede258b32c50f6cc69baaf5f4f63bebcf1fb6c04d805ecd39d0def0
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00046.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b4acf8378a26617f6aba5d1e5103e4e3095666eea21f11d8fd1e1a494f95f84
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00047.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff2cf5b68e14a35c7b8956411ca92c9620227f4d39cfc110c3503529545063c
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00048.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19a6f54334dffdf530fd14133639526f711ba2421c5eecf6151a23232122c6c
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a55d5d0ec57acc27c321143a2eefd7945a94ef0ad13fabb013ad80691451c7e
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00050.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755c9c67b891f4e4711afa0f24168d624c19fb7a6709b7f64340dac95e81a560
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00051.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cc5604f4558ab8f433eb3ba4f1c6985e32c7dd33273a5624da6c63f1327e60
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00052.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818aaad5e042aa0a2b813fbfbbaa51679006248239a9d9e78471abcec0179a09
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00053.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b7c8a12d3070173e6dd98e78ae1134ddf1f67f459d36538113ed0317ef2e57
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00054.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d02ec0dc0e3d95d0814d0fcc3ba7534c8d3df1716e867735665d6b65851660d
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00055.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce06f1052f56c8c0b6d3c08bd225c314ce248ff57bb553e25613603b60925938
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00056.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44002e10f988ba3e88a77dabb72dcb7495fc4b033688db77600d6fa0184c5252
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00057.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948a8ea45ccb9ed240afe5a6e2dee33963daa0652e5157a1ab102c03b48c3f72
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00058.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89135f0e72d252986ec4f8a3dad537793c9faee06f72ef561ad119beca5b96a6
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00059.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9c8ca1964fffc89a5982eb5de25afce6cfa9eae92fb79e8748e45ff66f6d4ec
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00060.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b2a4fd79b6af730f6e8e620f2a2faa3815223e9c6bb1bdc28ee6dd03b22b216
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00061.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d5c605f203af1b1b117f485ccd0401016ce3e4b5bbaae00a417ce578e093b2
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00062.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b573bc288163bdebb379e46d76435604880298ae45ba0494c7d04f39538daae
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00063.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0ef680c4222b377627433873e885727126bf798b0a18bbf07ad40823b4f0707
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00064.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69db7103c6d9dddfa2e81b6a87850c2b483805b65aa6e3a9b97e65275d5d577
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00065.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6207e7a21abbbdb58fcbc442daa4102185ad4175675a7f186d1e08db63305aa
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00066.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:458bbb5e131c8080ffc1374a834bd1d70edccd319fc0e575c94aff8ea056597a
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00067.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0ef7dace3568051834056a070369a6c3640d1c5eee667b514e8d52fcdb22d0
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00068.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982e4e3abbb362ed349dbe75b728f3eedd1e49361f04d0aaf6cf8a53a34b4613
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00069.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c28a79f754ccb521799d93680906c57d06c8f44f3f7982acb9578c4c6784c3
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00070.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5107dce8b4b7a47a9f20216f39543665ed49cbdbedf1f6c1231abc54121ee742
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00071.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99726ff3992c3563ce01a55ae87f0506560baf4a57eff46b54a1480ec96d507a
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00072.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98099b131a2c71b73797ac94a75ecd96d37b514799886106c59de5a7f9a72037
+size 800004016

sft/qwen38-distill-step8032/frozen-model-00073.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b280311e74bda962affbc98219153703012b76345e525be2d72292e2a1760d
+size 800004016