Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
Finnish-NLP
/
Ahma-3B
like
12
Text Generation
Transformers
Safetensors
5 datasets
Finnish
llama
finnish
conversational
text-generation-inference
arxiv:
2302.13971
arxiv:
2302.06675
arxiv:
2305.16264
License:
apache-2.0
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
615b2a3
Ahma-3B
3 contributors
History:
24 commits
aapot
fix autotokenizer
615b2a3
verified
4 months ago
EasyLM
Update optimizers
5 months ago
.gitattributes
1.52 kB
initial commit
8 months ago
.gitignore
11 Bytes
Add easylm training code
8 months ago
README.md
332 Bytes
Update README.md
8 months ago
config.json
662 Bytes
Add 2-stage 1060k step model
4 months ago
convert_to_hf_model.sh
148 Bytes
Add easylm training code
8 months ago
generation_config.json
116 Bytes
Add 2-stage 1060k step model
4 months ago
model-00001-of-00002.safetensors
4.95 GB
LFS
Add 2-stage 1060k step model
4 months ago
model-00002-of-00002.safetensors
2.31 GB
LFS
Add 2-stage 1060k step model
4 months ago
model.safetensors.index.json
19.5 kB
Add 100k step model
8 months ago
pretrain_llama_3b.sh
2.58 kB
Update optimizers
5 months ago
special_tokens_map.json
414 Bytes
Add chat template tokenizer
5 months ago
tokenizer.json
4.84 MB
fix autotokenizer
4 months ago
tokenizer.model
1.4 MB
LFS
Update tokenizer
8 months ago
tokenizer.vocab
1.09 MB
Update tokenizer
8 months ago
tokenizer_config.json
2.9 kB
fix autotokenizer
4 months ago
train_sentencepiece.py
737 Bytes
Update tokenizer
8 months ago