katuni4ka commited on
Commit
20a79fd
1 Parent(s): e1b4030

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +36 -2
README.md CHANGED
@@ -29,7 +29,8 @@ The provided OpenVINO™ IR model is compatible with:
29
  * OpenVINO version 2024.1.0 and higher
30
  * Optimum Intel 1.16.0 and higher
31
 
32
- ## Running Model Inference
 
33
 
34
  1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
35
 
@@ -47,7 +48,7 @@ model_id = "OpenVINO/starcoder2-3b-int4-ov"
47
  tokenizer = AutoTokenizer.from_pretrained(model_id)
48
  model = OVModelForCausalLM.from_pretrained(model_id)
49
 
50
- inputs = tokenizer("def print_hello_world()", return_tensors="pt")
51
 
52
  outputs = model.generate(**inputs, max_length=200)
53
  text = tokenizer.batch_decode(outputs)[0]
@@ -56,6 +57,39 @@ print(text)
56
 
57
  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).
58
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
  ## Legal information
60
 
61
  The original model is distributed under [bigcode-openrail-m](https://www.bigcode-project.org/docs/pages/bigcode-openrail/) license. More details can be found in [bigcode/starcoder2-3b](https://huggingface.co/bigcode/starcoder2-3b).
 
29
  * OpenVINO version 2024.1.0 and higher
30
  * Optimum Intel 1.16.0 and higher
31
 
32
+ ## Running Model Inference with [Optimum Intel](https://huggingface.co/docs/optimum/intel/index)
33
+
34
 
35
  1. Install packages required for using [Optimum Intel](https://huggingface.co/docs/optimum/intel/index) integration with the OpenVINO backend:
36
 
 
48
  tokenizer = AutoTokenizer.from_pretrained(model_id)
49
  model = OVModelForCausalLM.from_pretrained(model_id)
50
 
51
+ inputs = tokenizer("What is OpenVINO?", return_tensors="pt")
52
 
53
  outputs = model.generate(**inputs, max_length=200)
54
  text = tokenizer.batch_decode(outputs)[0]
 
57
 
58
  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).
59
 
60
+ ## Running Model Inference with [OpenVINO GenAI](https://github.com/openvinotoolkit/openvino.genai)
61
+
62
+ 1. Install packages required for using OpenVINO GenAI.
63
+ ```
64
+ pip install openvino-genai huggingface_hub
65
+ ```
66
+
67
+ 2. Download model from HuggingFace Hub
68
+
69
+ ```
70
+ import huggingface_hub as hf_hub
71
+
72
+ model_id = "OpenVINO/starcoder2-3b-int4-ov"
73
+ model_path = "starcoder2-3b-int4-ov"
74
+
75
+ hf_hub.snapshot_download(model_id, local_dir=model_path)
76
+
77
+ ```
78
+
79
+ 3. Run model inference:
80
+
81
+ ```
82
+ import openvino_genai as ov_genai
83
+
84
+ device = "CPU"
85
+ pipe = ov_genai.LLMPipeline(model_path, device)
86
+ print(pipe.generate("def print_hello_world():"))
87
+ ```
88
+
89
+ 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)
90
+
91
+ 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).
92
+
93
  ## Legal information
94
 
95
  The original model is distributed under [bigcode-openrail-m](https://www.bigcode-project.org/docs/pages/bigcode-openrail/) license. More details can be found in [bigcode/starcoder2-3b](https://huggingface.co/bigcode/starcoder2-3b).