Description
Pretrained AutoGGUFModel model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP.phi_3.1_mini_4k_instruct_iq3_m is a English model prepared by lmstudio-community.
How to use
document = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
autoGGUFModel = AutoGGUFModel.pretrained("phi_3.1_mini_4k_instruct_iq3_m","en") \
.setInputCols(["document"]) \
.setOutputCol("completions") \
.setBatchSize(4) \
.setNPredict(20) \
.setNGpuLayers(99) \
.setTemperature(0.4) \
.setTopK(40) \
.setTopP(0.9) \
.setPenalizeNl(True)
pipeline = Pipeline().setStages([document, autoGGUFModel])
data = spark.createDataFrame([["Hello, I am a"]]).toDF("text")
result = pipeline.fit(data).transform(data)
result.select("completions").show(truncate = False)
val document = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val autoGGUFModel = AutoGGUFModel.pretrained("phi_3.1_mini_4k_instruct_iq3_m", "en")
.setInputCols("document")
.setOutputCol("completions")
.setBatchSize(4)
.setNPredict(20)
.setNGpuLayers(99)
.setTemperature(0.4f)
.setTopK(40)
.setTopP(0.9f)
.setPenalizeNl(true)
val pipeline = new Pipeline().setStages(Array(document, autoGGUFModel))
val data = Seq("Hello, I am a").toDF("text")
val result = pipeline.fit(data).transform(data)
result.select("completions").show(truncate = false)
Model Information
| Model Name: | phi_3.1_mini_4k_instruct_iq3_m |
| Compatibility: | Spark NLP 5.5.1+ |
| License: | Open Source |
| Edition: | Official |
| Input Labels: | [document] |
| Output Labels: | [completions] |
| Language: | en |
| Size: | 1.8 GB |
References
https://huggingface.co/lmstudio-community/Phi-3.1-mini-4k-instruct-GGUF