MLX
Safetensors
cohere
35b-beta-long-8bit / README.md
m-i's picture
Upload folder using huggingface_hub (#1)
c23415e verified
metadata
language:
  - en
  - zh
  - ja
  - de
license: gpl-3.0
tags:
  - mlx
datasets:
  - JosephusCheung/GuanacoDataset
  - meta-math/MetaMathQA
  - jondurbin/airoboros-3.1
  - WizardLM/WizardLM_evol_instruct_V2_196k
  - RyokoAI/ShareGPT52K
  - RyokoAI/Fandom23K
  - milashkaarshif/MoeGirlPedia_wikitext_raw_archive
  - wikipedia
  - wiki_lingua
  - garage-bAInd/Open-Platypus
  - LDJnr/Puffin
  - BAAI/COIG
  - TigerResearch/tigerbot-zhihu-zh-10k
  - liwu/MNBVC
  - teknium/openhermes
  - CausalLM/Refined-Anime-Text
  - microsoft/orca-math-word-problems-200k
  - m-a-p/CodeFeedback-Filtered-Instruction

mlx-community/35b-beta-long-8bit

The Model mlx-community/35b-beta-long-8bit was converted to MLX format from CausalLM/35b-beta-long using mlx-lm version 0.12.0.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/35b-beta-long-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)