LLäMmlein 120M
LLäMmlein 120M is a German LLaMa model trained from scratch using our adapted Tinyllama codebase on the German portion of RedPajama V2. To enhance data quality, we additionally deduplicated the dataset on paragraph level and filtered it using a token-to-word ratio filter. The resulting dataset can be found here.
We provide three model sizes:
-
LLäMmlein 120M ← You are here
Find more details on our page our page and our preprint!
Usage
You can use LLäMmlein with the transformers library.
(Optional: install flash-attn to achieve highest efficiency.)
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "LSX-UniWue/LLaMmlein_120M"
tokenizer = AutoTokenizer.from_pretrained("LSX-UniWue/LLaMmlein_120M")
model = AutoModelForCausalLM.from_pretrained("LSX-UniWue/LLaMmlein_120M")
Intermediate Checkpoints
In addition to the final model checkpoint, we publish intermediate checkpoints throughout the full training process as unique branches in this repository. A specific checkpoint can be loaded like this:
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "LSX-UniWue/LLaMmlein_120M"
revision = "iter-00420000-ckpt"
tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)
model = AutoModelForCausalLM.from_pretrained(model_id, revision=revision)
Next to the model itself each branch contains all datapoints that were used to train the model up to that point.
In the correspinding folder, named after the checkpoint, you can find several .log files (depending on the number of GPUs) of the following format:
{"time": 1739809392.679516,
"iter_num": 0,
"data_id": ["sha1:EDQMBYDCYBLDAZH3MGYM276BM2DEHPPJ", "sha1:SAJCI75DRHZZFGQORV66NB5FVWUAVLFH", "sha1:7RBZV2MCEM4TUGBBWGTFQAKTWUOGETZU", "sha1:234M32IMLZF7455AKOFWDP6HT6YXAYB4", "sha1:2BIZ7LLSHRK5GUGPZM2GM55APTDKBUG2", "sha1:OF7OI77ZT7ROXGMB6LL4RSRANX7REAYK", "sha1:LGPUOCOV3MKETI5F3IHVGZPD4M26NNJL", "sha1:SHIHUW7FJTP5YHFFV2JZ2CAHUVMKK7XG"],
"file_id": [0, 0, 0, 0, 0, 0, 0, 0],
"process_rank": 0}
Note: Our earlier models from the paper, which do not include data logging, are available at:
License
We release the LLäMmlein models under a research-only RAIL-M license. See license.md for details. Data Take Down