Views
No views yet
1from peft import PeftModel
2from transformers import AutoModelForCausalLM, AutoTokenizer
3
4base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
5model = PeftModel.from_pretrained(base_model, "your-hf-username/your-model-name")
6tokenizer = AutoTokenizer.from_pretrained("your-hf-username/your-model-name")
7
8[More Information Needed]
9
10## Training Details
11
12### Training Data
13
14<!-- 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. -->
15
16[More Information Needed]
17
18### Training Procedure
19
20<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
21
22#### Preprocessing [optional]
23
24[More Information Needed]
25
26
27#### Training Hyperparameters
28
29- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
30
31#### Speeds, Sizes, Times [optional]
32
33<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
34
35[More Information Needed]
36
37## Evaluation
38
39<!-- This section describes the evaluation protocols and provides the results. -->
40
41### Testing Data, Factors & Metrics
42
43#### Testing Data
44
45<!-- This should link to a Dataset Card if possible. -->
46
47[More Information Needed]
48
49#### Factors
50
51<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
52
53[More Information Needed]
54
55#### Metrics
56
57<!-- These are the evaluation metrics being used, ideally with a description of why. -->
58
59[More Information Needed]
60
61### Results
62
63[More Information Needed]
64
65#### Summary
66
67
68
69## Model Examination [optional]
70
71<!-- Relevant interpretability work for the model goes here -->
72
73[More Information Needed]
74
75## Environmental Impact
76
77<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
78
79Carbon 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).
80
81- **Hardware Type:** [More Information Needed]
82- **Hours used:** [More Information Needed]
83- **Cloud Provider:** [More Information Needed]
84- **Compute Region:** [More Information Needed]
85- **Carbon Emitted:** [More Information Needed]
86
87## Technical Specifications [optional]
88
89### Model Architecture and Objective
90
91[More Information Needed]
92
93### Compute Infrastructure
94
95[More Information Needed]
96
97#### Hardware
98
99[More Information Needed]
100
101#### Software
102
103[More Information Needed]
104
105## Citation [optional]
106
107<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
108
109**BibTeX:**
110
111[More Information Needed]
112
113**APA:**
114
115[More Information Needed]
116
117## Glossary [optional]
118
119<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
120
121[More Information Needed]
122
123## More Information [optional]
124
125[More Information Needed]
126
127## Model Card Authors [optional]
128
129[More Information Needed]
130
131## Model Card Contact
132
133[More Information Needed]
134### Framework versions
135
136- PEFT 0.14.0