danielhanchen commited on
Commit
e3015f9
1 Parent(s): 2626aff

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +103 -159
README.md CHANGED
@@ -1,199 +1,143 @@
1
  ---
 
 
 
2
  library_name: transformers
3
- tags: []
 
 
 
4
  ---
5
 
6
- # Model Card for Model ID
7
 
8
- <!-- Provide a quick summary of what the model is/does. -->
9
 
 
 
10
 
 
11
 
12
- ## Model Details
13
-
14
- ### Model Description
15
-
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
-
36
- ## Uses
37
-
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
-
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
-
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
-
70
- ## How to Get Started with the Model
71
-
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
 
80
- <!-- 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. -->
 
 
 
 
 
 
 
81
 
82
- [More Information Needed]
 
 
83
 
84
- ### Training Procedure
85
 
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
 
88
- #### Preprocessing [optional]
 
 
 
 
 
89
 
90
- [More Information Needed]
91
 
 
 
 
92
 
93
- #### Training Hyperparameters
94
 
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
 
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- 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).
146
-
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
-
155
- ### Model Architecture and Objective
156
 
157
- [More Information Needed]
158
 
159
- ### Compute Infrastructure
160
 
161
- [More Information Needed]
162
 
163
- #### Hardware
 
164
 
165
- [More Information Needed]
 
 
 
 
 
166
 
167
- #### Software
168
 
169
- [More Information Needed]
170
 
171
- ## Citation [optional]
 
 
 
 
 
172
 
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
 
175
- **BibTeX:**
176
 
177
- [More Information Needed]
 
178
 
179
- **APA:**
 
180
 
181
- [More Information Needed]
 
 
 
 
 
182
 
183
- ## Glossary [optional]
184
 
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
 
 
 
 
186
 
187
- [More Information Needed]
 
 
 
 
188
 
189
- ## More Information [optional]
 
 
 
 
 
190
 
191
- [More Information Needed]
 
 
 
 
 
 
192
 
193
- ## Model Card Authors [optional]
 
194
 
195
- [More Information Needed]
196
 
197
- ## Model Card Contact
198
 
199
- [More Information Needed]
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
3
+ language:
4
+ - en
5
  library_name: transformers
6
+ license: apache-2.0
7
+ tags:
8
+ - unsloth
9
+ - transformers
10
  ---
11
 
12
+ # Finetune Llama 3.1, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
13
 
14
+ We have a free Google Colab Tesla T4 notebook for Llama 3.1 (8B) here: https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing
15
 
16
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/unsloth)
17
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
18
 
19
+ ## ✨ Finetune for Free
20
 
21
+ All notebooks are **beginner friendly**! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
 
23
+ | Unsloth supports | Free Notebooks | Performance | Memory use |
24
+ |-----------------|--------------------------------------------------------------------------------------------------------------------------|-------------|----------|
25
+ | **Llama-3.1 8b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing) | 2.4x faster | 58% less |
26
+ | **Phi-3.5 (mini)** | [▶️ Start on Colab](https://colab.research.google.com/drive/1lN6hPQveB_mHSnTOYifygFcrO8C1bxq4?usp=sharing) | 2x faster | 50% less |
27
+ | **Gemma-2 9b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing) | 2.4x faster | 58% less |
28
+ | **Mistral 7b** | [▶️ Start on Colab](https://colab.research.google.com/drive/1Dyauq4kTZoLewQ1cApceUQVNcnnNTzg_?usp=sharing) | 2.2x faster | 62% less |
29
+ | **TinyLlama** | [▶️ Start on Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing) | 3.9x faster | 74% less |
30
+ | **DPO - Zephyr** | [▶️ Start on Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) | 1.9x faster | 19% less |
31
 
32
+ - This [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing) is useful for ShareGPT ChatML / Vicuna templates.
33
+ - This [text completion notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing) is for raw text. This [DPO notebook](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing) replicates Zephyr.
34
+ - \* Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
35
 
 
36
 
37
+ # Qwen2.5-Math-1.5B-Instruct
38
 
39
+ > [!Warning]
40
+ > <div align="center">
41
+ > <b>
42
+ > 🚨 Qwen2.5-Math mainly supports solving English and Chinese math problems through CoT and TIR. We do not recommend using this series of models for other tasks.
43
+ > </b>
44
+ > </div>
45
 
46
+ ## Introduction
47
 
48
+ In August 2024, we released the first series of mathematical LLMs - [Qwen2-Math](https://qwenlm.github.io/blog/qwen2-math/) - of our Qwen family. A month later, we have upgraded it and open-sourced **Qwen2.5-Math** series, including base models **Qwen2.5-Math-1.5B/7B/72B**, instruction-tuned models **Qwen2.5-Math-1.5B/7B/72B-Instruct**, and mathematical reward model **Qwen2.5-Math-RM-72B**.
49
+
50
+ Unlike Qwen2-Math series which only supports using Chain-of-Thught (CoT) to solve English math problems, Qwen2.5-Math series is expanded to support using both CoT and Tool-integrated Reasoning (TIR) to solve math problems in both Chinese and English. The Qwen2.5-Math series models have achieved significant performance improvements compared to the Qwen2-Math series models on the Chinese and English mathematics benchmarks with CoT.
51
 
52
+ ![](http://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen2.5/qwen2.5-math-pipeline.jpeg)
53
 
54
+ While CoT plays a vital role in enhancing the reasoning capabilities of LLMs, it faces challenges in achieving computational accuracy and handling complex mathematical or algorithmic reasoning tasks, such as finding the roots of a quadratic equation or computing the eigenvalues of a matrix. TIR can further improve the model's proficiency in precise computation, symbolic manipulation, and algorithmic manipulation. Qwen2.5-Math-1.5B/7B/72B-Instruct achieve 79.7, 85.3, and 87.8 respectively on the MATH benchmark using TIR.
55
 
56
+ ## Model Details
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
 
58
 
59
+ For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen2.5-math/) and [GitHub repo](https://github.com/QwenLM/Qwen2.5-Math).
60
 
 
61
 
62
+ ## Requirements
63
+ * `transformers>=4.37.0` for Qwen2.5-Math models. The latest version is recommended.
64
 
65
+ > [!Warning]
66
+ > <div align="center">
67
+ > <b>
68
+ > 🚨 This is a must because <code>transformers</code> integrated Qwen2 codes since <code>4.37.0</code>.
69
+ > </b>
70
+ > </div>
71
 
72
+ For requirements on GPU memory and the respective throughput, see similar results of Qwen2 [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).
73
 
74
+ ## Quick Start
75
 
76
+ > [!Important]
77
+ >
78
+ > **Qwen2.5-Math-1.5B-Instruct** is an instruction model for chatting;
79
+ >
80
+ > **Qwen2.5-Math-1.5B** is a base model typically used for completion and few-shot inference, serving as a better starting point for fine-tuning.
81
+ >
82
 
83
+ ### 🤗 Hugging Face Transformers
84
 
85
+ Qwen2.5-Math can be deployed and infered in the same way as [Qwen2.5](https://github.com/QwenLM/Qwen2.5). Here we show a code snippet to show you how to use the chat model with `transformers`:
86
 
87
+ ```python
88
+ from transformers import AutoModelForCausalLM, AutoTokenizer
89
 
90
+ model_name = "Qwen/Qwen2.5-Math-1.5B-Instruct"
91
+ device = "cuda" # the device to load the model onto
92
 
93
+ model = AutoModelForCausalLM.from_pretrained(
94
+ model_name,
95
+ torch_dtype="auto",
96
+ device_map="auto"
97
+ )
98
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
99
 
100
+ prompt = "Find the value of $x$ that satisfies the equation $4x+5 = 6x+7$."
101
 
102
+ # CoT
103
+ messages = [
104
+ {"role": "system", "content": "Please reason step by step, and put your final answer within \\boxed{}."},
105
+ {"role": "user", "content": prompt}
106
+ ]
107
 
108
+ # TIR
109
+ messages = [
110
+ {"role": "system", "content": "Please integrate natural language reasoning with programs to solve the problem above, and put your final answer within \\boxed{}."},
111
+ {"role": "user", "content": prompt}
112
+ ]
113
 
114
+ text = tokenizer.apply_chat_template(
115
+ messages,
116
+ tokenize=False,
117
+ add_generation_prompt=True
118
+ )
119
+ model_inputs = tokenizer([text], return_tensors="pt").to(device)
120
 
121
+ generated_ids = model.generate(
122
+ **model_inputs,
123
+ max_new_tokens=512
124
+ )
125
+ generated_ids = [
126
+ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
127
+ ]
128
 
129
+ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
130
+ ```
131
 
132
+ ## Citation
133
 
134
+ If you find our work helpful, feel free to give us a citation.
135
 
136
+ ```
137
+ @article{yang2024qwen2,
138
+ title={Qwen2 technical report},
139
+ author={Yang, An and Yang, Baosong and Hui, Binyuan and Zheng, Bo and Yu, Bowen and Zhou, Chang and Li, Chengpeng and Li, Chengyuan and Liu, Dayiheng and Huang, Fei and others},
140
+ journal={arXiv preprint arXiv:2407.10671},
141
+ year={2024}
142
+ }
143
+ ```