doberst's picture
Upload 4 files
e4cd053 verified
metadata
license: apache-2.0
inference: false
base_model: berkeley-nest/Starling-LM-7B-alpha
base_model_relation: quantized
tags:
  - green
  - p7
  - llmware-chat
  - gguf

starling-lm-7b-alpha-gguf

starling-lm-7b-alpha-gguf is a GGUF Q4_K_M int4 quantized version of Berkeley Nest's popular finetune of mistral, providing a very fast, very small inference implementation.

starling-lm-7b-alpha-gguf is a leading chat finetuned version of mistral 7b.

Model Description

  • Developed by: berkeley-nest
  • Quantized by: llmware
  • Model type: mistral-7b
  • Parameters: 7 billion
  • Model Parent: berkeley-nest/Starling-LM-7B-alpha
  • Language(s) (NLP): English
  • License: Apache 2.0
  • Uses: General purpose chat
  • RAG Benchmark Accuracy Score: NA
  • Quantization: int4

Model Card Contact

llmware on github

llmware on hf

llmware website