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 +1,43 @@
+---
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: mlx
+tags:
+- reasoning
+- olympiad
+- mathematics
+- science
+- reinforcement-learning
+- test-time-scaling
+- long-context
+- mlx
+base_model: Simplified-Reasoning/SU-01
+---
+
+# mlx-community/SU-01-4bit
+
+This model [mlx-community/SU-01-4bit](https://huggingface.co/mlx-community/SU-01-4bit) was
+converted to MLX format from [Simplified-Reasoning/SU-01](https://huggingface.co/Simplified-Reasoning/SU-01)
+using mlx-lm version **0.31.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/SU-01-4bit")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True, return_dict=False,
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].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" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|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 %}
+        {%- 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 %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n<think>\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,435 @@
+{
+    "architectures": [
+        "Qwen3MoeForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "decoder_sparse_step": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "max_position_embeddings": 262144,
+    "max_window_layers": 48,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_moe",
+    "moe_intermediate_size": 768,
+    "norm_topk_prob": true,
+    "num_attention_heads": 32,
+    "num_experts": 128,
+    "num_experts_per_tok": 8,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 4,
+    "output_router_logits": false,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "model.layers.0.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.1.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.2.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.28.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.30.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.32.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.33.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.34.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.35.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.36.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.37.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.38.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.39.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.40.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.41.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.42.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.43.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.44.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.45.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.46.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.47.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine",
+        "model.layers.0.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.1.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.2.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.3.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.4.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.5.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.6.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.7.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.8.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.9.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.10.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.11.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.12.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.13.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.14.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.15.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.16.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.17.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.18.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.19.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.20.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.21.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.22.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.23.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.24.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.25.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.26.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.27.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.28.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.29.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.30.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.31.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.32.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.33.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.34.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.35.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.36.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.37.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.38.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.39.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.40.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.41.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.42.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.43.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.44.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.45.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.46.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        },
+        "model.layers.47.mlp.gate": {
+            "group_size": 64,
+            "bits": 8
+        }
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 10000000,
+    "router_aux_loss_coef": 0.001,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "transformers_version": "4.57.1",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f97ac8cc5d49eec718cbd97a9a852c680400e9c354b1e9438ff72db06624715
+size 5321473414

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdf1ba273582b9736c70612734f9813c3015ae7a74bae387ff4ac0bd4154864e
+size 5366644780

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cf32e620094ef287404f2178f960bf4fc799c83ab6d4f905b683103311cf9d0
+size 5276887419

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bfb10fd18349bd0f9bcd85fb115c4c6ee3a232fdaede178a4624464c93864ac
+size 1216066381

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "tool_parser_type": "json_tools",
+  "unk_token": null
+}