README.md

metadata

language:
  - en
  - ja
license: apache-2.0
library_name: transformers
tags:
  - mlx
datasets:
  - databricks/databricks-dolly-15k
  - llm-jp/databricks-dolly-15k-ja
  - llm-jp/oasst1-21k-en
  - llm-jp/oasst1-21k-ja
  - llm-jp/oasst2-33k-en
  - llm-jp/oasst2-33k-ja
programming_language:
  - C
  - C++
  - C#
  - Go
  - Java
  - JavaScript
  - Lua
  - PHP
  - Python
  - Ruby
  - Rust
  - Scala
  - TypeScript
pipeline_tag: text-generation
inference: false

mlx-community/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-4bit

This model was converted to MLX format from llm-jp/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0 using mlx-lm version 0.12.0. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)