metadata
library_name: transformers
license: apache-2.0
base_model: Heralax/Augmentoolkit-DataSpecialist-v0.1
tags:
- axolotl
- generated_from_trainer
- mlx
- mlx-my-repo
datasets:
- 29_mil_asstr.jsonl
- 40mil_gutenberg.jsonl
- hle-1_formatted_2mil.jsonl
- 11_mil_fineweb.jsonl
- multiturn_segments_shard_01.json
- multiturn_segments_shard_02.json
- singleturn_segments_shard_01.json
- singleturn_segments_shard_02.json
- openhermes2_5_shard_01.json
- openhermes2_5_shard_02.json
- openthoughts-1.parquet
- openthoughts-2.parquet
- qwq_10million.jsonl
- bluemoon-6mil.json
model-index:
- name: datagen-sft-1
results: []
LukasF/Augmentoolkit-DataSpecialist-v0.1-mlx-4Bit
The Model LukasF/Augmentoolkit-DataSpecialist-v0.1-mlx-4Bit was converted to MLX format from Heralax/Augmentoolkit-DataSpecialist-v0.1 using mlx-lm version 0.22.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("LukasF/Augmentoolkit-DataSpecialist-v0.1-mlx-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)