alicekyting commited on
Commit
06f5614
1 Parent(s): 3fff91c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +71 -168
README.md CHANGED
@@ -5,9 +5,8 @@ tags: []
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
 
@@ -17,183 +16,87 @@ tags: []
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]
 
5
 
6
  # Model Card for Model ID
7
 
8
+ This model is a 4-bit quantized version of Qwen2-Audio-7B-Instruct.
9
+ (https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct)
 
10
 
11
  ## Model Details
12
 
 
16
 
17
  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
18
 
19
+ - **Developed:** based on the original Qwen model by Alibaba Cloud
20
+ - **Model type:** Audio-Text Multimodal Large Language Model
 
 
 
 
 
21
 
22
+ ### Model Sources
23
 
24
  <!-- Provide the basic links for the model. -->
25
 
26
+ - **Repository:** https://huggingface.co/Qwen/Qwen2-Audio-7B-Instruct
 
 
27
 
28
  ## Uses
29
 
30
  <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
31
+ The 4-bit quantization allows for reduced memory usage and potentially faster inference times, especially on hardware with limited resources.
32
+ However, there might be a slight degradation in performance compared to the full-precision model.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
 
34
  ## Bias, Risks, and Limitations
35
 
36
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
37
+ GPU is needed
 
 
 
 
 
 
 
38
 
39
  ## How to Get Started with the Model
40
 
41
+ Refer to the Qwen2-Audio-7B-Instruct model page on Hugging Face for usage examples and code snippets.
42
+
43
+ To use this model, you'll need to have the transformers library installed, along with bitsandbytes for 4-bit quantization support.
44
+
45
+ Here's a basic example of how to load and use the model:
46
+
47
+ ```python
48
+ import torch
49
+ from io import BytesIO
50
+ from urllib.request import urlopen
51
+ import librosa
52
+ from transformers import Qwen2AudioForConditionalGeneration, AutoProcessor, BitsAndBytesConfig
53
+
54
+ processor = AutoProcessor.from_pretrained("alicekyting/Qwen2-Audio-7B-Instruct-4bit")
55
+ bnb_config = BitsAndBytesConfig(
56
+ load_in_4bit=True,
57
+ bnb_4bit_compute_dtype=torch.float16
58
+ )
59
+ model = Qwen2AudioForConditionalGeneration.from_pretrained(
60
+ "alicekyting/Qwen2-Audio-7B-Instruct-4bit",
61
+ device_map="auto",
62
+ quantization_config=bnb_config
63
+ )
64
+
65
+ conversation = [
66
+ {'role': 'system', 'content': 'You are a helpful assistant.'},
67
+ {"role": "user", "content": [
68
+ {"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/glass-breaking-151256.mp3"},
69
+ {"type": "text", "text": "What's that sound?"},
70
+ ]},
71
+ {"role": "assistant", "content": "It is the sound of glass shattering."},
72
+ {"role": "user", "content": [
73
+ {"type": "text", "text": "What can you do when you hear that?"},
74
+ ]},
75
+ {"role": "assistant", "content": "Stay alert and cautious, and check if anyone is hurt or if there is any damage to property."},
76
+ {"role": "user", "content": [
77
+ {"type": "audio", "audio_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-Audio/audio/1272-128104-0000.flac"},
78
+ {"type": "text", "text": "What does the person say?"},
79
+ ]},
80
+ ]
81
+ text = processor.apply_chat_template(conversation, add_generation_prompt=True, tokenize=False)
82
+ audios = []
83
+ for message in conversation:
84
+ if isinstance(message["content"], list):
85
+ for ele in message["content"]:
86
+ if ele["type"] == "audio":
87
+ audios.append(
88
+ librosa.load(
89
+ BytesIO(urlopen(ele['audio_url']).read()),
90
+ sr=processor.feature_extractor.sampling_rate,
91
+ mono=True
92
+ )[0]
93
+ )
94
+
95
+ inputs = processor(text=text, audios=audios, return_tensors="pt", padding=True)
96
+ inputs = {k: v.to(model.device) for k, v in inputs.items()}
97
+
98
+ generate_ids = model.generate(**inputs, max_length=256)
99
+ generate_ids = generate_ids[:, inputs['input_ids'].size(1):]
100
+
101
+ response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
102
+ print(response)