lhallee commited on
Commit
c495ee8
·
verified ·
1 Parent(s): 9c12a1b

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +10 -9
README.md CHANGED
@@ -1,11 +1,12 @@
1
  ---
2
  library_name: transformers
 
3
  tags:
4
- - biology
5
- - esm
6
- - protein
7
- - protein-language-model
8
- - masked-language-modeling
9
  ---
10
 
11
  # ESM++ 6B
@@ -13,6 +14,8 @@ tags:
13
  [ESM++](https://github.com/Synthyra/FastPLMs) is a Hugging Face compatible implementation of [Biohub ESMC](https://biohub.ai/esm/protein) ([license](https://github.com/Biohub/esm/blob/main/LICENSE.md)).
14
  This checkpoint corresponds to the 6 billion parameter ESMC model released as [`biohub/ESMC-6B`](https://huggingface.co/biohub/ESMC-6B).
15
 
 
 
16
  The 6B model has 80 transformer layers, hidden size 2560, and 40 attention heads. It is large enough that `dtype=torch.bfloat16` or `torch.float16` plus `device_map="auto"` is usually the practical loading path.
17
 
18
  ## Attention Backends
@@ -93,7 +96,6 @@ embedding_dict = model.embed_dataset(
93
  "MSEQWENCE",
94
  "MPRTEIN",
95
  ],
96
- tokenizer=model.tokenizer,
97
  batch_size=1,
98
  max_len=1024,
99
  full_embeddings=False,
@@ -112,7 +114,6 @@ For residue-level embeddings, set `full_embeddings=True`:
112
  ```python
113
  residue_embeddings = model.embed_dataset(
114
  sequences=["MALWMRLLPLLALLALWGPDPAAA"],
115
- tokenizer=model.tokenizer,
116
  batch_size=1,
117
  max_len=1024,
118
  full_embeddings=True,
@@ -126,7 +127,6 @@ For very large datasets, write embeddings directly to SQLite:
126
  ```python
127
  model.embed_dataset(
128
  fasta_path="proteins.fasta",
129
- tokenizer=model.tokenizer,
130
  batch_size=1,
131
  max_len=1024,
132
  pooling_types=["mean"],
@@ -222,13 +222,14 @@ model = ESMplusplusForMaskedLM.from_pretrained_esm("esmc-6b")
222
  ```
223
 
224
  The source repository is [`biohub/ESMC-6B`](https://huggingface.co/biohub/ESMC-6B).
 
225
 
226
  ## Citation
227
 
228
  ```bibtex
229
  @misc{FastPLMs,
230
  author={Hallee, Logan and Bichara, David and Gleghorn, Jason P.},
231
- title={FastPLMs: Fast, efficient, protein language model inference from Huggingface AutoModel.},
232
  year={2024},
233
  url={https://huggingface.co/Synthyra/ESMplusplus_6B},
234
  DOI={10.57967/hf/3726},
 
1
  ---
2
  library_name: transformers
3
+ license: mit
4
  tags:
5
+ - biology
6
+ - esm
7
+ - protein
8
+ - protein-language-model
9
+ - masked-language-modeling
10
  ---
11
 
12
  # ESM++ 6B
 
14
  [ESM++](https://github.com/Synthyra/FastPLMs) is a Hugging Face compatible implementation of [Biohub ESMC](https://biohub.ai/esm/protein) ([license](https://github.com/Biohub/esm/blob/main/LICENSE.md)).
15
  This checkpoint corresponds to the 6 billion parameter ESMC model released as [`biohub/ESMC-6B`](https://huggingface.co/biohub/ESMC-6B).
16
 
17
+ This repository includes the Biohub ESM MIT license in `LICENSE`.
18
+
19
  The 6B model has 80 transformer layers, hidden size 2560, and 40 attention heads. It is large enough that `dtype=torch.bfloat16` or `torch.float16` plus `device_map="auto"` is usually the practical loading path.
20
 
21
  ## Attention Backends
 
96
  "MSEQWENCE",
97
  "MPRTEIN",
98
  ],
 
99
  batch_size=1,
100
  max_len=1024,
101
  full_embeddings=False,
 
114
  ```python
115
  residue_embeddings = model.embed_dataset(
116
  sequences=["MALWMRLLPLLALLALWGPDPAAA"],
 
117
  batch_size=1,
118
  max_len=1024,
119
  full_embeddings=True,
 
127
  ```python
128
  model.embed_dataset(
129
  fasta_path="proteins.fasta",
 
130
  batch_size=1,
131
  max_len=1024,
132
  pooling_types=["mean"],
 
222
  ```
223
 
224
  The source repository is [`biohub/ESMC-6B`](https://huggingface.co/biohub/ESMC-6B).
225
+ The Biohub ESM license is available at https://github.com/Biohub/esm/blob/main/LICENSE.md.
226
 
227
  ## Citation
228
 
229
  ```bibtex
230
  @misc{FastPLMs,
231
  author={Hallee, Logan and Bichara, David and Gleghorn, Jason P.},
232
+ title={FastPLMs: Fast, efficient, protein language model inference from Hugging Face AutoModel.},
233
  year={2024},
234
  url={https://huggingface.co/Synthyra/ESMplusplus_6B},
235
  DOI={10.57967/hf/3726},