Fill-Mask
Transformers
Safetensors
nucengram
feature-extraction
biology
genomics
dna
masked-lm
custom_code
Instructions to use FreakingPotato/NucEngram with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FreakingPotato/NucEngram with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="FreakingPotato/NucEngram", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("FreakingPotato/NucEngram", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add mini S123 variant
Browse files- mini/config.json +50 -0
- mini/model.safetensors +3 -0
mini/config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "nucengram",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"NucEngramModel"
|
| 5 |
+
],
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "configuration_nucengram.NucEngramConfig",
|
| 8 |
+
"AutoModel": "modeling_nucengram.NucEngramModel",
|
| 9 |
+
"AutoModelForMaskedLM": "modeling_nucengram.NucEngramForMaskedLM"
|
| 10 |
+
},
|
| 11 |
+
"backbone": {
|
| 12 |
+
"vocab_size": 9,
|
| 13 |
+
"hidden_size": 384,
|
| 14 |
+
"intermediate_size": 1024,
|
| 15 |
+
"num_hidden_layers": 8,
|
| 16 |
+
"num_attention_heads": 6,
|
| 17 |
+
"max_position_embeddings": 8192,
|
| 18 |
+
"local_attention": 128,
|
| 19 |
+
"rope_theta_global": 160000.0,
|
| 20 |
+
"rope_theta_local": 10000.0,
|
| 21 |
+
"attn_implementation": "sdpa",
|
| 22 |
+
"tie_word_embeddings": true
|
| 23 |
+
},
|
| 24 |
+
"engram": {
|
| 25 |
+
"ngram_orders": [
|
| 26 |
+
3,
|
| 27 |
+
4,
|
| 28 |
+
5,
|
| 29 |
+
6,
|
| 30 |
+
8
|
| 31 |
+
],
|
| 32 |
+
"n_heads_per_order": 4,
|
| 33 |
+
"d_mem": 48,
|
| 34 |
+
"layer_inject_ids": [
|
| 35 |
+
1,
|
| 36 |
+
4
|
| 37 |
+
],
|
| 38 |
+
"use_conv": true,
|
| 39 |
+
"gate_temp": 1.0,
|
| 40 |
+
"seed": 0,
|
| 41 |
+
"hidden_size": 384,
|
| 42 |
+
"vocab_size": 9,
|
| 43 |
+
"pad_id": 0
|
| 44 |
+
},
|
| 45 |
+
"max_length": 8192,
|
| 46 |
+
"pad_token_id": 0,
|
| 47 |
+
"hidden_size": 384,
|
| 48 |
+
"torch_dtype": "float32",
|
| 49 |
+
"transformers_version": "5.7.0"
|
| 50 |
+
}
|
mini/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b25d4380ebd27c5559ad1774257b1c974fb58b4284fdc2ae634174d370a4f623
|
| 3 |
+
size 599645508
|