初始化项目，由ModelHub XC社区提供模型

Model: cs-552-2026-thinking-tokens/math_model
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

EVAL_REPORT.md

@@ -0,0 +1,207 @@
+# Automated MNLP evaluation report
+
+- **Model repo:** [`cs-552-2026-thinking-tokens/math_model`](https://huggingface.co/cs-552-2026-thinking-tokens/math_model)
+- **Owner(s):** group **thinking-tokens**
+- **Generated at:** 2026-05-19T03:22:52+00:00 (UTC)
+- **Pipeline:** [mnlp-project-ci](https://github.com/eric11eca/mnlp-project-ci)
+
+_This PR is opened automatically by the course CI. It is **non-blocking** — you do not need to merge it. The next nightly run will refresh this file._
+
+## Summary
+
+| Benchmark | Accuracy | Status |
+|---|---:|---|
+| Math | 0.3900 | ok |
+| Knowledge | — | not run |
+| Multilingual | — | not run |
+| Safety | — | not run |
+
+## Sample completions
+
+_Prompts are intentionally omitted to avoid revealing benchmark contents. For multi-completion problems, only one completion is shown per sample._
+
+### Math
+
+**Correct** (1 shown)
+
+- **reference**: `194`
+- **overall** (2/8 completions correct)
+- **extracted** (✓): `194`
+- **completion**:
+
+    ```text
+    We are given a $194 \times 194$ board, and we are to find the **least positive integer $k$** such that we can choose $k$ cells to mark, and there is **exactly one tiling** of the board by $1 \times 2$ and $2 \times 1$ dominoes in which **every domino contains at most one marked cell**.
+    
+    ---
+    
+    ### Step 1: Understand the problem
+    
+    We are to find the **smallest number of marked cells** such that:
+    
+    - Th
+    
+    ... [truncated 823 chars] ...
+    
+    t can be **involving marked cells** is $k$.
+    - Since there are 18818 dominoes, the number of dominoes that **do not involve marked cells** is $18818 - k$.
+    
+    We want **exactly one** tiling where **every domino has at most one marked cell**.
+    
+    This is equivalent to saying that the **marked cells** must be placed in such a way that **each domino is uniquely determined** by the marked cells.
+    
+    This is a very strong condition.
+    
+    ---
+    
+    ### Step 4: What is the minimum number of marked cells?
+    
+    This is a classic problem in **combinatorics and tiling theory**.
+    
+    We are to find the **minimum number of marked cells** such that:
+    
+    - There is **exactly one tiling** of the board with dominoes.
+    - In this tiling, **every domino contains at most one marked cell**.
+    
+    This is equivalent to saying that the **marked cells** are **independent** in the tiling, and the tiling is **unique**.
+    
+    This is a well-known result in combinatorics and tiling theory.
+    
+    ---
+    
+    ### Step 5: Known result
+    
+    It is known that the **minimum number of marked cells** needed to ensure **exactly one tiling** with dominoes, where **every domino contains at most one marked cell**, is:
+    
+    $$
+    \boxed{194}
+    $$
+    
+    ---
+    
+    ### Final Answer:
+    
+    $$
+    \boxed{194}
+    $$
+    ```
+
+**Incorrect** (1 shown)
+
+- **reference**: `$g(x)=c, g(x)=\lceil x \rceil, g(x)=\lfloor x \rfloor$`
+- **overall** (0/8 completions correct)
+- **extracted** (✗): `h(x) = x`
+- **completion**:
+
+    ```text
+    We are given a functional equation:
+    
+    $$
+    h(x) = h\left( \frac{h(bx - a) + a}{b} \right)
+    $$
+    
+    for all $ x \in \mathbb{Q} $, $ a \in \mathbb{Z} $, and $ b \in \mathbb{N} $.
+    
+    We are to find all functions $ h : \mathbb{Q} \to \mathbb{Z} $ satisfying this equation.
+    
+    ---
+    
+    ### Step 1: Try simple candidate functions
+    
+    Let’s try a function of the form:
+    
+    $$
+    h(x) = kx + c
+    $$
+    
+    for some constants $ k, c \in \math
+    
+    ... [truncated 822 chars] ...
+    
+    n, only possible for specific $ a $ and $ b $, not all.
+    
+    ---
+    
+    ### Step 7: Try the function $ h(x) = \frac{a}{b} $
+    
+    Let’s try:
+    
+    $$
+    h(x) = \frac{a}{b}
+    $$
+    
+    But this is not a function from $ \mathbb{Q} \to \mathbb{Z} $, because $ \frac{a}{b} \in \mathbb{Q} $, not necessarily an integer.
+    
+    ---
+    
+    ### Step 8: Try $ h(x) = \lfloor x \rfloor $ again
+    
+    We tried this, and it failed.
+    
+    ---
+    
+    ### Step 9: Try a function that maps rational numbers to integers in a specific way
+    
+    Let’s consider the **identity function**:
+    
+    $$
+    h(x) = x
+    $$
+    
+    Then:
+    
+    $$
+    h(x) = x
+    $$
+    $$
+    h(bx - a) = bx - a
+    $$
+    $$
+    \frac{h(bx - a) + a}{b} = \frac{bx - a + a}{b} = x
+    $$
+    
+    So the equation becomes:
+    
+    $$
+    x = x
+    $$
+    
+    Which is **true**.
+    
+    So $ h(x) = x $ is a solution.
+    
+    ---
+    
+    ### Step 10: Check if there are other solutions
+    
+    Suppose $ h(x) = x $ is a solution.
+    
+    Now suppose $ h(x) = x + c $ for some constant $ c \in \mathbb{Z} $
+    
+    Then:
+    
+    $$
+    h(x) = x + c
+    $$
+    $$
+    h(bx - a) = bx - a + c
+    $$
+    $$
+    \frac{h(bx - a) + a}{b} = \frac{bx - a + c + a}{b} = x + \frac{c}{b}
+    $$
+    
+    So:
+    
+    $$
+    x + c = x + \frac{c}{b} \Rightarrow c = \frac{c}{b}
+    $$
+    
+    This is only possible if $ c = 0 $, so $ h(x) = x $ is the **only** solution.
+    
+    ---
+    
+    ### ✅ Final Answer:
+    
+    $$
+    \boxed{h(x) = x}
+    $$
+    ```

README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen3-1.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-1.7B
+- grpo
+- lora
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e5cc8341460a53b0c38a013e84cdad5131a121606140f4d5c7f0d7cfe91ddb
+size 139512976

chat_template.jinja

@@ -0,0 +1,19 @@
+{%- set enable_thinking = true %}
+{%- set boxed_instruction = "You are a mathematical reasoning model. Solve the problem carefully. Use short scratch work to demonstrate the essential intermediate steps. Answer before the token budget (4096 in total) is exhausted. Return the final answer in exact form whenever possible. Put only the final answer inside a LaTeX \\boxed{} expression. Do not put explanations, units, or multiple answers inside the box unless the problem explicitly asks for them. " %}
+{%- if messages|length > 0 and messages[0]['role'] == 'system' %}
+    {%- set system_message = boxed_instruction + "\n\n" + messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = boxed_instruction %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{{- '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}
+{%- for message in loop_messages %}
+    {{- '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>\n' }}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if not enable_thinking %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,63 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_new_tokens": 4096,
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.9,
+  "transformers_version": "5.7.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169ad53ec313c3a34b06c0809216e4fc072cce444a5d4ff2b59690d064130ed5
+size 3441185608

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98e770c015cce8d813cfc775b5f855c01653c4616adb737eeb165594353ccf8
+size 279257723

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40146296f05d9345f852100181c1eb04c0626f043acb8da4beda393517827245
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e565bbdfb0e22cb241294cbce26748684b2a03180d8f3809e706740b6ec3630f
+size 1465

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1dfbce22d8487292784256a5f8170a87f2952c85a6741795b7e2c965f21f1c
+size 7185