README.md

metadata

license: wtfpl
language:
  - en
  - zh
  - ja
  - de
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
base_model: CausalLM/35b-beta-long
tags:
  - mlx

mlx-community/CausalLM-35b-beta-long-4bit

The Model mlx-community/CausalLM-35b-beta-long-4bit was converted to MLX format from CausalLM/35b-beta-long using mlx-lm version 0.20.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/CausalLM-35b-beta-long-4bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)