katuni4ka commited on
Commit
63fee37
1 Parent(s): 43f6b37

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +33 -2
README.md CHANGED
@@ -15,7 +15,8 @@ The provided OpenVINO™ IR model is compatible with:
15
  * OpenVINO version 2024.4.0 and higher
16
  * Optimum Intel 1.20.0 and higher
17
 
18
- ## Running Model Inference
 
19
 
20
  1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
21
 
@@ -33,7 +34,7 @@ model_id = "OpenVINO/codegen-6B-multi-fp16-ov"
33
  tokenizer = AutoTokenizer.from_pretrained(model_id)
34
  model = OVModelForCausalLM.from_pretrained(model_id)
35
 
36
- inputs = tokenizer("What is OpenVINO?", return_tensors="pt")
37
 
38
  outputs = model.generate(**inputs, max_length=200)
39
  text = tokenizer.batch_decode(outputs)[0]
@@ -42,6 +43,36 @@ print(text)
42
 
43
  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).
44
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  ## Limitations
46
 
47
  Check the original model card for [original model card](https://huggingface.co/Salesforce/codegen-6B-multi) for limitations.
 
15
  * OpenVINO version 2024.4.0 and higher
16
  * Optimum Intel 1.20.0 and higher
17
 
18
+ ## Running Model Inference with [Optimum Intel](https://huggingface.co/docs/optimum/intel/index)
19
+
20
 
21
  1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
22
 
 
34
  tokenizer = AutoTokenizer.from_pretrained(model_id)
35
  model = OVModelForCausalLM.from_pretrained(model_id)
36
 
37
+ inputs = tokenizer("def print_hello_world():", return_tensors="pt")
38
 
39
  outputs = model.generate(**inputs, max_length=200)
40
  text = tokenizer.batch_decode(outputs)[0]
 
43
 
44
  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).
45
 
46
+ ## Running Model Inference with [OpenVINO GenAI](https://github.com/openvinotoolkit/openvino.genai)
47
+
48
+ 1. Install packages required for using OpenVINO GenAI.
49
+ ```
50
+ pip install openvino-genai huggingface_hub
51
+ ```
52
+
53
+ 2. Download model from HuggingFace Hub
54
+
55
+ ```
56
+ import huggingface_hub as hf_hub
57
+
58
+ model_id = "OpenVINO/codegen-6B-multi-fp16-ov"
59
+ model_path = "codegen-6B-multi-fp16-ov"
60
+
61
+ hf_hub.snapshot_download(model_id, local_dir=model_path)
62
+
63
+ ```
64
+
65
+ 3. Run model inference:
66
+
67
+ ```
68
+ import openvino_genai as ov_genai
69
+
70
+ device = "CPU"
71
+ pipe = ov_genai.LLMPipeline(model_path, device)
72
+ print(pipe.generate("def print_hello_world():", max_length=200))
73
+ ```
74
+
75
+ More GenAI usage examples can be found in OpenVINO GenAI library [docs](https://github.com/openvinotoolkit/openvino.genai/blob/master/src/README.md) and [samples](https://github.com/openvinotoolkit/openvino.genai?tab=readme-ov-file#openvino-genai-samples)
76
  ## Limitations
77
 
78
  Check the original model card for [original model card](https://huggingface.co/Salesforce/codegen-6B-multi) for limitations.