Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
tangledgroup
/
tangled-llama-v-128k-base-v0.1
like
0
Follow
TangledGroup
2
Text Generation
Transformers
Safetensors
21 datasets
107 languages
llama
litgpt
litdata
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
951a420
tangled-llama-v-128k-base-v0.1
/
scripts
2 contributors
History:
23 commits
mtasic85
pretrain model, extend from 5 to 8 epochs
951a420
26 days ago
TRAIN.md
1.88 kB
pretrain model, extend from 5 to 8 epochs
26 days ago
prepare_pretrain_dataset.py
5.82 kB
general pretrain data generation
27 days ago
pretrain-model.yaml
4.94 kB
pretrain model, extend from 5 to 8 epochs
26 days ago
requirements.in
240 Bytes
trained new 128k tokenizer
28 days ago
train_tokenizer.py
9.01 kB
new tokenizer 38400
27 days ago