Description
Phi-3.5-mini is a lightweight, state-of-the-art open model built upon datasets used for Phi-3 - synthetic data and filtered publicly available websites - with a focus on very high-quality, reasoning dense data. The model belongs to the Phi-3 model family and supports 128K token context length.
Predicted Entities
How to use
import sparknlp
from sparknlp.base import *
from sparknlp.annotator import *
from pyspark.ml import Pipeline
document = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
Phi3 = Phi3Transformer \
.loadSavedModel(EXPORT_PATH, spark) \
.setMaxOutputLength(50) \
.setDoSample(True) \
.setInputCols(["documents"]) \
.setOutputCol("generation")
pipeline = Pipeline().setStages([document, Phi3])
data = spark.createDataFrame([["Hello, I am a"]]).toDF("text")
result = pipeline.fit(data).transform(data)
result.select("completions").show(truncate = False)
Model Information
| Model Name: | phi_3.5_mini_instruct_int4 |
| Compatibility: | Spark NLP 6.0.4+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [documents] |
| Output Labels: | [generation] |
| Language: | en |
| Size: | 2.2 GB |