FluidInference
/

phi-4-mini-instruct-int4-ov-npu

Text Generation

Model card Files Files and versions

bweng commited on Jun 26

Commit

d1abcbc

·

verified ·

1 Parent(s): e16912c

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -92,7 +92,7 @@ hf_hub.snapshot_download(model_id, local_dir=model_path)
 ```
 import openvino_genai as ov_genai
 device = "NPU"
-pipe = ov_genai.LLMPipeline(model_path, "NPU", MAX_PROMPT_LEN=4096, MIN_RESPONSE_LEN=1024, CACHE_DIR="./cache")
 # Create a proper GenerationConfig object
 gen_config = GenerationConfig(apply_chat_template=True, max_new_tokens=1024)

 ```
 import openvino_genai as ov_genai
 device = "NPU"
+pipe = ov_genai.LLMPipeline(model_path, "NPU", MAX_PROMPT_LEN=4096, CACHE_DIR="./cache")
 # Create a proper GenerationConfig object
 gen_config = GenerationConfig(apply_chat_template=True, max_new_tokens=1024)