sylwia-kuros commited on
Commit
475694f
·
verified ·
1 Parent(s): 912fe1c

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!-- Metadata section, filled in yaml format. Usually contains info about license -->
2
+ ---
3
+ license: mit
4
+ license_link: https://choosealicense.com/licenses/mit/
5
+ ---
6
+ <!-- Model name used as model card title -->
7
+ # LCM_Dreamshaper_v7-fp16-ov
8
+ <!-- Original model reference -->
9
+ * Model creator: [SimianLuo](https://huggingface.co/SimianLuo)
10
+ * Original model: [SimianLuo/LCM_Dreamshaper_v7](https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7)
11
+
12
+ <!-- Description of converted model -->
13
+ ## Description
14
+
15
+ <!-- Comment and reference on NNCF applicable only for INT8 and INT4 models -->
16
+ This is [SimianLuo/LCM_Dreamshaper_v7](https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7) model converted to the [OpenVINO™ IR](https://docs.openvino.ai/2024/documentation/openvino-ir-format.html) (Intermediate Representation) format.
17
+
18
+ ## Compatibility
19
+
20
+ The provided OpenVINO™ IR model is compatible with:
21
+
22
+ * OpenVINO version 2024.1.0 and higher
23
+ * Optimum Intel 1.16.0 and higher
24
+
25
+ ## Running Model Inference
26
+
27
+ <!-- Example model usage -->
28
+
29
+ 1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
30
+
31
+ ```
32
+ pip install optimum[openvino]
33
+ ```
34
+
35
+ 2. Run model inference:
36
+
37
+ <!-- Usage example can be adopted from original model usage example -->
38
+
39
+ ```
40
+ from transformers import AutoTokenizer
41
+ from optimum.intel.openvino import OVModelForCausalLM
42
+
43
+ model_id = "OpenVINO/LCM_Dreamshaper_v7-fp16-ov"
44
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
45
+ model = OVModelForCausalLM.from_pretrained(model_id)
46
+
47
+ inputs = tokenizer("What is OpenVINO?", return_tensors="pt")
48
+
49
+ outputs = model.generate(**inputs, max_length=200)
50
+ text = tokenizer.batch_decode(outputs)[0]
51
+ print(text)
52
+ ```
53
+
54
+ For more examples and possible optimizations, refer to the [OpenVINO Large Language Model Inference Guide](https://docs.openvino.ai/2024/learn-openvino/llm_inference_guide.html).
55
+
56
+ ## Legal information
57
+
58
+ <!-- Note about original model license -->
59
+ The original model is distributed under [mit](https://choosealicense.com/licenses/mit/) license. More details can be found in [SimianLuo/LCM_Dreamshaper_v7](https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7).
60
+
61
+ ## Disclaimer
62
+
63
+ Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See [Intel’s Global Human Rights Principles](https://www.intel.com/content/dam/www/central-libraries/us/en/documents/policy-human-rights.pdf). Intel’s products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.