初始化项目，由ModelHub XC社区提供模型
Model: DOEJGI/GenomeOcean-500M Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
44
LICENSE
Normal file
44
LICENSE
Normal file
@@ -0,0 +1,44 @@
|
||||
*** License Agreement ***
|
||||
|
||||
genomeocean: a pretrained microbial genome foundational model (genomeoceanLLM)
|
||||
Copyright (c) 2025, The Regents of the University of California, through Lawrence Berkeley
|
||||
National Laboratory (subject to receipt of any required approvals from the U.S. Dept. of Energy)
|
||||
and Northwestern University. All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
|
||||
(1) Redistributions of source code must retain the above copyright notice,
|
||||
this list of conditions and the following disclaimer.
|
||||
|
||||
(2) Redistributions in binary form must reproduce the above copyright
|
||||
notice, this list of conditions and the following disclaimer in the
|
||||
documentation and/or other materials provided with the distribution.
|
||||
|
||||
(3) Neither the name of the University of California, Lawrence Berkeley
|
||||
National Laboratory, U.S. Dept. of Energy, Northwestern University nor
|
||||
the names of its contributors may be used to endorse or promote products
|
||||
derived from this software without specific prior written permission.
|
||||
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
||||
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
||||
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
|
||||
IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
|
||||
INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
|
||||
NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
|
||||
PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
|
||||
WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
||||
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY
|
||||
OF SUCH DAMAGE.
|
||||
|
||||
You are under no obligation whatsoever to provide any bug fixes, patches,
|
||||
or upgrades to the features, functionality or performance of the source
|
||||
code ("Enhancements") to anyone; however, if you choose to make your
|
||||
Enhancements available either publicly, or directly to Lawrence Berkeley
|
||||
National Laboratory, without imposing a separate written license agreement
|
||||
for such Enhancements, then you hereby grant the following license: a
|
||||
non-exclusive, royalty-free perpetual license to install, use, modify,
|
||||
prepare derivative works, incorporate into other computer software,
|
||||
distribute, and sublicense such enhancements or derivative works thereof,
|
||||
in binary and source code form.
|
||||
41
README.md
Normal file
41
README.md
Normal file
@@ -0,0 +1,41 @@
|
||||
---
|
||||
license: bsd
|
||||
tags:
|
||||
- biology
|
||||
- genomics
|
||||
- metagenomics
|
||||
- DNA
|
||||
- microbiome
|
||||
---
|
||||
|
||||
This is the base model of GenomeOcean-500M. It is trained with Causal Language Modeling (CLM) and uses a BPE tokenizer with 4096 tokens. It supports a maximum sequence length of 1024 tokens (~5kbp).
|
||||
|
||||
Please see our official implementation on our [Github](https://github.com/jgi-genomeocean/genomeocean).
|
||||
|
||||
Quick start.
|
||||
|
||||
```
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(
|
||||
"pGenomeOcean/GenomeOcean-4B",
|
||||
trust_remote_code=True,
|
||||
padding_side="left",
|
||||
)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
"pGenomeOcean/GenomeOcean-4B",
|
||||
trust_remote_code=True,
|
||||
torch_dtype=torch.bfloat16,
|
||||
attn_implementation="flash_attention_2",
|
||||
).to("cuda")
|
||||
```
|
||||
|
||||
|
||||
Copyright Notice
|
||||
|
||||
genomeocean: a pretrained microbial genome foundational model (genomeoceanLLM) ” Copyright (c) 2025, The Regents of the University of California, through Lawrence Berkeley National Laboratory (subject to receipt of any required approvals from the U.S. Dept. of Energy) and Northwestern University. All rights reserved.
|
||||
|
||||
If you have questions about your rights to use or distribute this software, please contact Berkeley Lab's Intellectual Property Office at IPO@lbl.gov.
|
||||
|
||||
NOTICE. This Software was developed under funding from the U.S. Department of Energy and the U.S. Government consequently retains certain rights. As such, the U.S. Government has been granted for itself and others acting on its behalf a paid-up, nonexclusive, irrevocable, worldwide license in the Software to reproduce, distribute copies to the public, prepare derivative works, and perform publicly and display publicly, and to permit others to do so.
|
||||
31
config.json
Normal file
31
config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"_name_or_path": "./model/model_mistral_500M",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"classifier_dropout": 0.1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"is_causal": true,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 8,
|
||||
"num_hidden_layers": 14,
|
||||
"num_key_value_heads": 8,
|
||||
"output_router_logits": false,
|
||||
"pad_token_id": 3,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"router_aux_loss_coef": 0.02,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.38.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 4096
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 3,
|
||||
"transformers_version": "4.38.2"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b6315d77656839e51328d2ba04924fe7585782b7e1edd2fa5649fbbcd31b68cb
|
||||
size 1082234168
|
||||
37
special_tokens_map.json
Normal file
37
special_tokens_map.json
Normal file
@@ -0,0 +1,37 @@
|
||||
{
|
||||
"cls_token": {
|
||||
"content": "[CLS]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"mask_token": {
|
||||
"content": "[MASK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"sep_token": {
|
||||
"content": "[SEP]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "[UNK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
8327
tokenizer.json
Normal file
8327
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
52
tokenizer_config.json
Normal file
52
tokenizer_config.json
Normal file
@@ -0,0 +1,52 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "[UNK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "[CLS]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "[SEP]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "[MASK]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"cls_token": "[CLS]",
|
||||
"mask_token": "[MASK]",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "[PAD]",
|
||||
"sep_token": "[SEP]",
|
||||
"tokenizer_class": "PreTrainedTokenizerFast",
|
||||
"unk_token": "[UNK]"
|
||||
}
|
||||
Reference in New Issue
Block a user