Qwen3 (0 6B) Phone Deployment

🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.
🦥 Unsloth Zoo will now patch everything to make training faster!
Unsloth: You selected full finetuning support, but 4bit / 8bit is enabled - disabling LoRA / QLoRA.
==((====))==  Unsloth 2025.12.9: Fast Qwen3 patching. Transformers: 4.56.2.
   \\   /|    Tesla T4. Num GPUs = 1. Max memory: 14.741 GB. Platform: Linux.
O^O/ \_/ \    Torch: 2.9.0+cu126. CUDA: 7.5. CUDA Toolkit: 12.6. Triton: 3.5.0
\        /    Bfloat16 = FALSE. FA [Xformers = 0.0.33.post1. FA2 = False]
 "-____-"     Free license: http://github.com/unslothai/unsloth
Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!
Unsloth: Float16 full finetuning uses more memory since we upcast weights to float32.

model.safetensors:   0%|          | 0.00/1.19G [00:00<?, ?B/s]

generation_config.json:   0%|          | 0.00/237 [00:00<?, ?B/s]

tokenizer_config.json: 0.00B [00:00, ?B/s]

vocab.json: 0.00B [00:00, ?B/s]

merges.txt: 0.00B [00:00, ?B/s]

tokenizer.json:   0%|          | 0.00/11.4M [00:00<?, ?B/s]

added_tokens.json:   0%|          | 0.00/707 [00:00<?, ?B/s]

special_tokens_map.json:   0%|          | 0.00/614 [00:00<?, ?B/s]

chat_template.jinja: 0.00B [00:00, ?B/s]

Unsloth: Applying QAT to mitigate quantization degradation

README.md:   0%|          | 0.00/603 [00:00<?, ?B/s]

data/cot-00000-of-00001.parquet:   0%|          | 0.00/106M [00:00<?, ?B/s]

Generating cot split:   0%|          | 0/19252 [00:00<?, ? examples/s]

README.md:   0%|          | 0.00/982 [00:00<?, ?B/s]

data/train-00000-of-00001.parquet:   0%|          | 0.00/117M [00:00<?, ?B/s]

Generating train split:   0%|          | 0/100000 [00:00<?, ? examples/s]

Dataset({
,    features: ['expected_answer', 'problem_type', 'problem_source', 'generation_model', 'pass_rate_72b_tir', 'problem', 'generated_solution', 'inference_mode'],
,    num_rows: 19252
,})

Dataset({
,    features: ['conversations', 'source', 'score'],
,    num_rows: 100000
,})

Map:   0%|          | 0/19252 [00:00<?, ? examples/s]

"<|im_start|>user\nGiven $\\sqrt{x^2+165}-\\sqrt{x^2-52}=7$ and $x$ is positive, find all possible values of $x$.<|im_end|>\n<|im_start|>assistant\n<think>\nOkay, let's see. I need to solve the equation √(x² + 165) - √(x² - 52) = 7, and find all positive values of x. Hmm, radicals can be tricky, but maybe if I can eliminate the square roots by squaring both sides. Let me try that.\n\nFirst, let me write down the equation again to make sure I have it right:\n\n√(x² + 165) - √(x² - 52) = 7.\n\nOkay, so the idea is to isolate one of the radicals and then square both sides. Let me try moving the second radical to the other side:\n\n√(x² + 165) = 7 + √(x² - 52).\n\nNow, if I square both sides, maybe I can get rid of the square roots. Let's do that:\n\n(√(x² + 165))² = (7 + √(x² - 52))².\n\nSimplifying the left side:\n\nx² + 165 = 49 + 14√(x² - 52) + (√(x² - 52))².\n\nThe right side is expanded using the formula (a + b)² = a² + 2ab + b². So the right side becomes 7² + 2*7*√(x² - 52) + (√(x² - 52))², which is 49 + 14√(x² - 52) + (x² - 52).\n\nSo putting it all together:\n\nx² + 165 = 49 + 14√(x² - 52) + x² - 52.\n\nHmm, let's simplify the right side. The x² terms will cancel out, right? Let's subtract x² from both sides:\n\n165 = 49 + 14√(x² - 52) - 52.\n\nSimplify the constants on the right:\n\n49 - 52 is -3, so:\n\n165 = -3 + 14√(x² - 52).\n\nNow, add 3 to both sides to isolate the radical term:\n\n165 + 3 = 14√(x² - 52).\n\nSo 168 = 14√(x² - 52).\n\nDivide both sides by 14:\n\n168 / 14 = √(x² - 52).\n\n12 = √(x² - 52).\n\nNow, square both sides again to eliminate the square root:\n\n12² = x² - 52.\n\n144 = x² - 52.\n\nAdd 52 to both sides:\n\n144 + 52 = x².\n\n196 = x².\n\nSo x = √196 = 14.\n\nBut wait, since the problem states that x is positive, we only take the positive root. So x = 14.\n\nBut hold on, when dealing with squaring equations, sometimes extraneous solutions can come up. I should check if this solution actually satisfies the original equation.\n\nLet's plug x = 14 back into the original equation:\n\n√(14² + 165) - √(14² - 52) = ?\n\nCalculate each term:\n\n14² is 196.\n\nSo first radical: √(196 + 165) = √361 = 19.\n\nSecond radical: √(196 - 52) = √144 = 12.\n\nSo 19 - 12 = 7, which is exactly the right-hand side. So yes, it checks out.\n\nTherefore, the only solution is x = 14. Since the problem says x is positive, we don't have to consider negative roots. So I think that's the answer.\n</think>\n\nTo solve the equation \\(\\sqrt{x^2 + 165} - \\sqrt{x^2 - 52} = 7\\) for positive \\(x\\), we proceed as follows:\n\n1. Start with the given equation:\n   \\[\n   \\sqrt{x^2 + 165} - \\sqrt{x^2 - 52} = 7\n   \\]\n\n2. Isolate one of the square roots by moving \\(\\sqrt{x^2 - 52}\\) to the right side:\n   \\[\n   \\sqrt{x^2 + 165} = 7 + \\sqrt{x^2 - 52}\n   \\]\n\n3. Square both sides to eliminate the square root on the left:\n   \\[\n   (\\sqrt{x^2 + 165})^2 = (7 + \\sqrt{x^2 - 52})^2\n   \\]\n   Simplifying both sides, we get:\n   \\[\n   x^2 + 165 = 49 + 14\\sqrt{x^2 - 52} + (x^2 - 52)\n   \\]\n\n4. Combine like terms on the right side:\n   \\[\n   x^2 + 165 = x^2 - 52 + 49 + 14\\sqrt{x^2 - 52}\n   \\]\n   Simplifying further:\n   \\[\n   x^2 + 165 = x^2 - 3 + 14\\sqrt{x^2 - 52}\n   \\]\n\n5. Subtract \\(x^2\\) from both sides:\n   \\[\n   165 = -3 + 14\\sqrt{x^2 - 52}\n   \\]\n\n6. Add 3 to both sides to isolate the term with the square root:\n   \\[\n   168 = 14\\sqrt{x^2 - 52}\n   \\]\n\n7. Divide both sides by 14:\n   \\[\n   12 = \\sqrt{x^2 - 52}\n   \\]\n\n8. Square both sides again to eliminate the square root:\n   \\[\n   12^2 = x^2 - 52\n   \\]\n   Simplifying:\n   \\[\n   144 = x^2 - 52\n   \\]\n\n9. Add 52 to both sides to solve for \\(x^2\\):\n   \\[\n   196 = x^2\n   \\]\n\n10. Take the positive square root (since \\(x\\) is positive):\n    \\[\n    x = \\sqrt{196} = 14\n    \\]\n\n11. Verify the solution by substituting \\(x = 14\\) back into the original equation:\n    \\[\n    \\sqrt{14^2 + 165} - \\sqrt{14^2 - 52} = \\sqrt{196 + 165} - \\sqrt{196 - 52} = \\sqrt{361} - \\sqrt{144} = 19 - 12 = 7\n    \\]\n    The solution checks out.\n\nThus, the only positive solution is:\n\\[\n\\boxed{14}\n\\]<|im_end|>\n"

Unsloth: Standardizing formats (num_proc=2):   0%|          | 0/100000 [00:00<?, ? examples/s]

'<|im_start|>user\nExplain what boolean operators are, what they do, and provide examples of how they can be used in programming. Additionally, describe the concept of operator precedence and provide examples of how it affects the evaluation of boolean expressions. Discuss the difference between short-circuit evaluation and normal evaluation in boolean expressions and demonstrate their usage in code. \n\nFurthermore, add the requirement that the code must be written in a language that does not support short-circuit evaluation natively, forcing the test taker to implement their own logic for short-circuit evaluation.\n\nFinally, delve into the concept of truthiness and falsiness in programming languages, explaining how it affects the evaluation of boolean expressions. Add the constraint that the test taker must write code that handles cases where truthiness and falsiness are implemented differently across different programming languages.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\nBoolean operators are logical operators used in programming to manipulate boolean values. They operate on one or more boolean operands and return a boolean result. The three main boolean operators are "AND" (&&), "OR" (||), and "NOT" (!).\n\nThe "AND" operator returns true if both of its operands are true, and false otherwise. For example:\n\n```python\nx = 5\ny = 10\nresult = (x > 0) and (y < 20)  # This expression evaluates to True\n```\n\nThe "OR" operator returns true if at least one of its operands is true, and false otherwise. For example:\n\n```python\nx = 5\ny = 10\nresult = (x > 0) or (y < 20)  # This expression evaluates to True\n```\n\nThe "NOT" operator negates the boolean value of its operand. It returns true if the operand is false, and false if the operand is true. For example:\n\n```python\nx = 5\nresult = not (x > 10)  # This expression evaluates to True\n```\n\nOperator precedence refers to the order in which operators are evaluated in an expression. It ensures that expressions are evaluated correctly. In most programming languages, logical AND has higher precedence than logical OR. For example:\n\n```python\nresult = True or False and False  # This expression is evaluated as (True or (False and False)), which is True\n```\n\nShort-circuit evaluation is a behavior where the second operand of a logical operator is not evaluated if the result can be determined based on the value of the first operand. In short-circuit evaluation, if the first operand of an "AND" operator is false, the second operand is not evaluated because the result will always be false. Similarly, if the first operand of an "OR" operator is true, the second operand is not evaluated because the result will always be true.\n\nIn programming languages that support short-circuit evaluation natively, you can use it to improve performance or avoid errors. For example:\n\n```python\nif x != 0 and (y / x) > 10:\n    # Perform some operation\n```\n\nIn languages without native short-circuit evaluation, you can implement your own logic to achieve the same behavior. Here\'s an example in pseudocode:\n\n```\nif x != 0 {\n    if (y / x) > 10 {\n        // Perform some operation\n    }\n}\n```\n\nTruthiness and falsiness refer to how non-boolean values are evaluated in boolean contexts. In many programming languages, non-zero numbers and non-empty strings are considered truthy, while zero, empty strings, and null/None values are considered falsy.\n\nWhen evaluating boolean expressions, truthiness and falsiness come into play. For example:\n\n```python\nx = 5\nresult = x  # The value of x is truthy, so result is also truthy\n```\n\nTo handle cases where truthiness and falsiness are implemented differently across programming languages, you can explicitly check the desired condition. For example:\n\n```python\nx = 5\nresult = bool(x)  # Explicitly converting x to a boolean value\n```\n\nThis ensures that the result is always a boolean value, regardless of the language\'s truthiness and falsiness rules.<|im_end|>\n'

19252
100000

19252
6417
0.2499902606256574

Unsloth: Tokenizing ["text"] (num_proc=4):   0%|          | 0/25669 [00:00<?, ? examples/s]

🦥 Unsloth: Padding-free auto-enabled, enabling faster training.

GPU = Tesla T4. Max memory = 14.741 GB.
3.518 GB of memory reserved.

==((====))==  Unsloth - 2x faster free finetuning | Num GPUs used = 1
   \\   /|    Num examples = 25,669 | Num Epochs = 1 | Total steps = 100
O^O/ \_/ \    Batch size per device = 2 | Gradient accumulation steps = 4
\        /    Data Parallel GPUs = 1 | Total batch size (2 x 4 x 1) = 8
 "-____-"     Trainable parameters = 751,632,384 of 751,632,384 (100.00% trained)

Unsloth: Will smartly offload gradients to save VRAM!

695.3901 seconds used for training.
11.59 minutes used for training.
Peak reserved memory = 10.562 GB.
Peak reserved memory for training = 7.044 GB.
Peak reserved memory % of max memory = 71.65 %.
Peak reserved memory for training % of max memory = 47.785 %.

Skipping import of cpp extensions due to incompatible torch version 2.9.0+cu126 for torchao version 0.14.0         Please see GitHub issue #2919 for more info
I tokenizers:regex.cpp:27] Registering override fallback regex
<frozen runpy>:128: RuntimeWarning: 'executorch.examples.models.qwen3.convert_weights' found in sys.modules after import of package 'executorch.examples.models.qwen3', but prior to execution of 'executorch.examples.models.qwen3.convert_weights'; this may result in unpredictable behaviour
Loading checkpoint...
Loading checkpoint from pytorch_model directory
Converting checkpoint...
Saving checkpoint...
Done.

  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
100   348  100   348    0     0    750      0 --:--:-- --:--:-- --:--:--   750

Skipping import of cpp extensions due to incompatible torch version 2.9.0+cu126 for torchao version 0.14.0         Please see GitHub issue #2919 for more info
I tokenizers:regex.cpp:27] Registering override fallback regex
[INFO 2026-01-02 09:17:24,012 utils.py:164] NumExpr defaulting to 2 threads.
[INFO 2026-01-02 09:17:25,160 export_llama_lib.py:781] Applying quantizers: []
[INFO 2026-01-02 09:17:26,240 export_llama_lib.py:703] Checkpoint dtype: torch.float32
[INFO 2026-01-02 09:17:26,240 custom_kv_cache.py:367] Replacing KVCache with CustomKVCache. This modifies the model in place.
[INFO 2026-01-02 09:17:26,383 custom_ops.py:34] Looking for libcustom_ops_aot_lib.so in /usr/local/lib/python3.12/dist-packages/executorch/extension/llm/custom_ops
[INFO 2026-01-02 09:17:26,386 custom_ops.py:39] Loading custom ops library: /usr/local/lib/python3.12/dist-packages/executorch/extension/llm/custom_ops/libcustom_ops_aot_lib.so
[INFO 2026-01-02 09:17:26,397 builder.py:192] Model after source transforms: Transformer(
  (tok_embeddings): Embedding(151936, 1024)
  (layers): ModuleList(
    (0-27): 28 x TransformerBlock(
      (attention): AttentionMHA(
        (q_norm_fn): RMSNorm()
        (k_norm_fn): RMSNorm()
        (wq): Linear(in_features=1024, out_features=2048, bias=False)
        (wk): Linear(in_features=1024, out_features=1024, bias=False)
        (wv): Linear(in_features=1024, out_features=1024, bias=False)
        (wo): Linear(in_features=2048, out_features=1024, bias=False)
        (rope): Rope()
        (kv_cache): CustomKVCache()
        (SDPA): SDPACustom()
      )
      (feed_forward): FeedForward(
        (w1): Linear(in_features=1024, out_features=3072, bias=False)
        (w2): Linear(in_features=3072, out_features=1024, bias=False)
        (w3): Linear(in_features=1024, out_features=3072, bias=False)
      )
      (attention_norm): RMSNorm()
      (ffn_norm): RMSNorm()
    )
  )
  (rope): Rope()
  (norm): RMSNorm()
  (output): Linear(in_features=1024, out_features=151936, bias=False)
)
[INFO 2026-01-02 09:17:26,442 builder.py:218] Exporting with:
[INFO 2026-01-02 09:17:26,446 builder.py:219] inputs: (tensor([[2, 3, 4]]), {'input_pos': tensor([0])})
[INFO 2026-01-02 09:17:26,446 builder.py:220] kwargs: None
[INFO 2026-01-02 09:17:26,446 builder.py:221] dynamic shapes: ({1: Dim('token_dim', min=0, max=128)}, {'input_pos': {0: 1}})
[INFO 2026-01-02 09:18:15,928 builder.py:255] Running canonical pass: RemoveRedundantTransposes
[INFO 2026-01-02 09:18:16,131 export_llama_lib.py:854] Lowering model using following partitioner(s): 
[INFO 2026-01-02 09:18:16,131 export_llama_lib.py:856] --> XnnpackDynamicallyQuantizedPartitioner
[INFO 2026-01-02 09:18:16,131 export_llama_lib.py:856] --> XnnpackPartitioner
[INFO 2026-01-02 09:18:16,131 builder.py:341] Using pt2e [] to quantizing the model...
[INFO 2026-01-02 09:18:16,131 builder.py:394] No quantizer provided, passing...
[INFO 2026-01-02 09:18:16,133 builder.py:216] Re-exporting with:
[INFO 2026-01-02 09:18:16,133 builder.py:219] inputs: (tensor([[2, 3, 4]]), {'input_pos': tensor([0])})
[INFO 2026-01-02 09:18:16,133 builder.py:220] kwargs: None
[INFO 2026-01-02 09:18:16,133 builder.py:221] dynamic shapes: ({1: Dim('token_dim', min=0, max=128)}, {'input_pos': {0: 1}})
/usr/local/lib/python3.12/dist-packages/executorch/exir/emit/_emitter.py:1594: UserWarning: Mutation on a buffer in the model is detected. ExecuTorch assumes buffers that are mutated in the graph have a meaningless initial state, only the shape and dtype will be serialized, unless a pass which sets meta["et_init_buffer"] to True such as InitializedMutableBufferPass is run.
  warnings.warn(
[INFO 2026-01-02 09:28:08,838 builder.py:511] Required memory for activation in bytes: [0, 243793984]
modelname: qwen3_0.6B_model
output_file: qwen3_0.6B_model.pte
[INFO 2026-01-02 09:28:15,301 utils.py:141] Saved exported program to qwen3_0.6B_model.pte

-rw-r--r-- 1 root root 472M Jan  2 09:28 qwen3_0.6B_model.pte