Views
No views yet
1from transformers import AutoModelForCausalLM, AutoTokenizer
2repo = "Wonder-Griffin/ZeusMM"
3tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
4model = AutoModelForCausalLM.from_pretrained(repo, trust_remote_code=True)
5prompt = "<|system|>You are Zeus.<|end|>\n<|user|>Say hi.<|end|>\n<|assistant|>"
6x = tok(prompt, return_tensors="pt")
7y = model.generate(**x, max_new_tokens=60, do_sample=True, top_p=0.9, temperature=0.9)
8print(tok.decode(y[0], skip_special_tokens=False))
9
10
11
12- **Developed by:** [More Information Needed]
13- **Funded by [optional]:** [More Information Needed]
14- **Shared by [optional]:** [More Information Needed]
15- **Model type:** [More Information Needed]
16- **Language(s) (NLP):** [More Information Needed]
17- **License:** [More Information Needed]
18- **Finetuned from model [optional]:** [More Information Needed]
19
20### Model Sources [optional]
21
22<!-- Provide the basic links for the model. -->
23
24- **Repository:** [More Information Needed]
25- **Paper [optional]:** [More Information Needed]
26- **Demo [optional]:** [More Information Needed]
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
32### Direct Use
33
34<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
35
36[More Information Needed]
37
38### Downstream Use [optional]
39
40<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
41
42[More Information Needed]
43
44### Out-of-Scope Use
45
46<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
47
48[More Information Needed]
49
50## Bias, Risks, and Limitations
51
52<!-- This section is meant to convey both technical and sociotechnical limitations. -->
53
54[More Information Needed]
55
56### Recommendations
57
58<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
59
60Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
61
62## How to Get Started with the Model
63
64Use the code below to get started with the model.
65
66[More Information Needed]
67
68## Training Details
69
70### Training Data
71
72<!-- 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. -->
73
74[More Information Needed]
75
76### Training Procedure
77
78<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
79
80#### Preprocessing [optional]
81
82[More Information Needed]
83
84
85#### Training Hyperparameters
86
87- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
88
89#### Speeds, Sizes, Times [optional]
90
91<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
92
93[More Information Needed]
94
95## Evaluation
96
97<!-- This section describes the evaluation protocols and provides the results. -->
98
99### Testing Data, Factors & Metrics
100
101#### Testing Data
102
103<!-- This should link to a Dataset Card if possible. -->
104
105[More Information Needed]
106
107#### Factors
108
109<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
110
111[More Information Needed]
112
113#### Metrics
114
115<!-- These are the evaluation metrics being used, ideally with a description of why. -->
116
117[More Information Needed]
118
119### Results
120
121[More Information Needed]
122
123#### Summary
124
125
126
127## Model Examination [optional]
128
129<!-- Relevant interpretability work for the model goes here -->
130
131[More Information Needed]
132
133## Environmental Impact
134
135<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
136
137Carbon 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).
138
139- **Hardware Type:** [More Information Needed]
140- **Hours used:** [More Information Needed]
141- **Cloud Provider:** [More Information Needed]
142- **Compute Region:** [More Information Needed]
143- **Carbon Emitted:** [More Information Needed]
144
145## Technical Specifications [optional]
146
147### Model Architecture and Objective
148
149[More Information Needed]
150
151### Compute Infrastructure
152
153[More Information Needed]
154
155#### Hardware
156
157[More Information Needed]
158
159#### Software
160
161[More Information Needed]
162
163## Citation [optional]
164
165<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
166
167**BibTeX:**
168
169[More Information Needed]
170
171**APA:**
172
173[More Information Needed]
174
175## Glossary [optional]
176
177<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
178
179[More Information Needed]
180
181## More Information [optional]
182
183[More Information Needed]
184
185## Model Card Authors [optional]
186
187[More Information Needed]
188
189## Model Card Contact
190
191[More Information Needed]