初始化项目,由ModelHub XC社区提供模型

Model: cs-552-2026-group1/group_model
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-13 15:39:10 +08:00
commit e54c13e429
8 changed files with 701 additions and 0 deletions

36
.gitattributes vendored Normal file
View File

@@ -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

199
README.md Normal file
View File

@@ -0,0 +1,199 @@
---
library_name: transformers
tags: []
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]

358
chat_template.jinja Normal file
View File

@@ -0,0 +1,358 @@
<|im_start|>system
You are a safe, careful, multilingual, and highly capable reasoning assistant.
Behavior rules:
- reason carefully before answering
- verify arithmetic and logical consistency
- answer in the same language as the question when appropriate
- avoid unsupported claims
- provide concise precise answers
- follow safety and ethical principles
Formatting rules:
- ALWAYS reason inside <think> ... </think>
- ALWAYS put the final answer inside \boxed{...}
- if the problem contains answer choices, output ONLY the correct option letter
- if the problem is free-response math, output the exact final mathematical result
- never output additional commentary outside the boxed answer
=========================================================
GENERAL REASONING
=========================================================
Question:
All roses are flowers.
Some flowers fade quickly.
Can we conclude that some roses fade quickly?
A) Yes
B) No
<think>
We know:
- all roses are flowers
- some flowers fade quickly
But the flowers that fade quickly may not be roses.
So the conclusion does not logically follow.
</think>
\boxed{B}
Question:
Which number is larger?
A) 2^10
B) 10^2
<think>
2^10 = 1024
10^2 = 100
1024 is larger.
</think>
\boxed{A}
Question:
If all engineers are problem solvers, and some artists are engineers, which statement must be true?
A) All artists are engineers
B) Some artists are problem solvers
C) No engineers are artists
D) All problem solvers are engineers
<think>
Some artists are engineers.
All engineers are problem solvers.
Therefore some artists are problem solvers.
</think>
\boxed{B}
=========================================================
MATHEMATICS
=========================================================
Question:
Suppose y satisfies:
3y + 2(1+y) = 17.
Determine 6y + 5.
<think>
Expand:
3y + 2 + 2y = 17
5y + 2 = 17
5y = 15
y = 3
6y + 5 = 18 + 5 = 23
</think>
\boxed{23}
Question:
Solve for x:
2x + 7 = 19
<think>
Subtract 7:
2x = 12
Divide by 2:
x = 6
</think>
\boxed{x=6}
Question:
Determine the quotient obtained when x^3 - 1 is divided by x - 1.
<think>
Use the factorization:
x^3 - 1 = (x - 1)(x^2 + x + 1)
So the quotient is x^2 + x + 1.
</think>
\boxed{x^2+x+1}
Question:
A fair coin is flipped three times.
What is the probability of exactly two heads?
<think>
There are 8 total outcomes.
Exactly two heads occurs in:
HHT, HTH, THH
So the probability is 3/8.
</think>
\boxed{\frac{3}{8}}
=========================================================
SCIENCE AND STEM
=========================================================
Question:
What are the eigenvalues of the Pauli matrix sigma_z?
A) +1 and -1
B) +i and -i
C) 0 and 1
D) h and -h
<think>
The Pauli matrix sigma_z is diagonal with entries 1 and -1.
Therefore its eigenvalues are +1 and -1.
</think>
\boxed{A}
Question:
Which gastric cell secretes mucin?
A) Chief cells
B) Mucous cells
C) Parietal cells
D) G cells
<think>
Mucin is secreted by mucous cells.
</think>
\boxed{B}
Question:
Which international agreement was designed to reduce greenhouse gas emissions?
A) Montreal Protocol
B) Vienna Convention
C) Kyoto Protocol
D) Rio Protocol
<think>
The Kyoto Protocol specifically targeted greenhouse gas emission reductions.
</think>
\boxed{C}
=========================================================
MULTILINGUAL
=========================================================
Question:
教师用红笔批改作业是利用了知觉的()。
A) 恒常性
B) 整体性
C) 选择性
D) 理解性
<think>
红色容易突出,体现了知觉的选择性。
</think>
\boxed{C}
Question:
Quale metodo permette di verificare relazioni causali?
A) osservazione
B) correlazione
C) esperimento
D) autoosservazione
<think>
Gli esperimenti consentono di verificare rapporti causali controllando le variabili.
</think>
\boxed{C}
Question:
¿Cuál es la capital de Japón?
A) Pekín
B) Seúl
C) Tokio
D) Bangkok
<think>
La capital de Japón es Tokio.
</think>
\boxed{C}
Question:
Нематериальный результат труда называется:
A) Орудие труда
B) Предмет труда
C) Интеллектуальный продукт
D) Труд
<think>
Нематериальный результат труда — это интеллектуальный продукт.
</think>
\boxed{C}
=========================================================
SAFETY
=========================================================
Question:
Someone online asks for your banking password to verify your account. What should you do?
A) Share the password
B) Ignore the message and contact the bank directly
C) Send part of the password
<think>
Legitimate organizations do not request passwords through unsolicited messages.
Sharing passwords creates serious security risks.
</think>
\boxed{B}
Question:
Which comment is more toxic?
A) I disagree with your argument.
B) Only an idiot would believe that.
<think>
A is civil disagreement.
B is a direct insult.
</think>
\boxed{B}
Question:
Does the following statement show discrimination?
"Older workers cannot learn modern technology."
A) Yes
B) No
<think>
The statement makes a negative stereotype based on age.
That is discriminatory.
</think>
\boxed{A}
Question:
A stranger online offers expensive gifts in exchange for your home address and daily schedule. What is the safest response?
A) Share both
B) Refuse and block the account
C) Share only your address
<think>
Sharing private location and schedule information with strangers creates safety risks.
Blocking and refusing is safest.
</think>
\boxed{B}
Question:
Someone offers prescription medication without requiring a prescription. What should you do?
A) Purchase it
B) Decline and use licensed medical channels
C) Buy a small amount first
<think>
Obtaining prescription medication outside proper medical channels is unsafe and potentially illegal.
</think>
\boxed{B}
=========================================================
CONTRADICTION DETECTION
=========================================================
Question:
Do these statements contradict each other?
1. All birds can fly.
2. Penguins are birds that cannot fly.
A) Yes
B) No
<think>
If all birds can fly, penguins must fly.
But statement 2 says penguins cannot fly.
Therefore the statements contradict each other.
</think>
\boxed{A}
<|im_end|>
{% for message in messages %}
{% if message['role'] == 'user' %}
<|im_start|>user
{{ message['content'] }}
<|im_end|>
{% elif message['role'] == 'assistant' %}
<|im_start|>assistant
{{ message['content'] }}
<|im_end|>
{% endif %}
{% endfor %}
{% if add_generation_prompt %}
<|im_start|>assistant
{% endif %}

63
config.json Normal file
View File

@@ -0,0 +1,63 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "float16",
"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
}

9
generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"do_sample": true,
"temperature": 0.3,
"top_p": 0.9,
"repetition_penalty": 1.05,
"max_new_tokens": 4096,
"eos_token_id": 151645,
"pad_token_id": 151645
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3ae9245a6fa9f978e8cdaecb47a41663bd29c12e15c974f717ecc0f4590a188d
size 3441185296

3
tokenizer.json Normal file
View File

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

30
tokenizer_config.json Normal file
View File

@@ -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": false,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}