Upload model
Browse files- README.md +9 -9
- config.json +58 -0
- model.safetensors +3 -0
README.md
CHANGED
|
@@ -1,15 +1,15 @@
|
|
| 1 |
---
|
| 2 |
-
tags:
|
| 3 |
-
- safe
|
| 4 |
-
- mamba
|
| 5 |
-
- molecular-generation
|
| 6 |
-
- smiles
|
| 7 |
-
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
model-index:
|
| 11 |
-
|
| 12 |
-
|
| 13 |
---
|
| 14 |
|
| 15 |
# SSM_20M
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
datasets:
|
| 3 |
+
- katielink/moses
|
| 4 |
+
tags:
|
| 5 |
+
- safe
|
| 6 |
+
- mamba
|
| 7 |
+
- molecular-generation
|
| 8 |
+
- smiles
|
| 9 |
+
- generated_from_trainer
|
| 10 |
model-index:
|
| 11 |
+
- name: SSM_20M
|
| 12 |
+
results: []
|
| 13 |
---
|
| 14 |
|
| 15 |
# SSM_20M
|
config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./result_and_evaluation/SSM_20M_little_dropout",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MambaModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_cfg": {},
|
| 7 |
+
"attn_layer_idx": [],
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"conv_kernel": 4,
|
| 10 |
+
"d_intermediate": 0,
|
| 11 |
+
"d_model": 512,
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"expand": 2,
|
| 15 |
+
"fused_add_norm": true,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 768,
|
| 18 |
+
"id2label": {
|
| 19 |
+
"0": "LABEL_0"
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.1,
|
| 22 |
+
"intermediate_size": 1536,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"LABEL_0": 0
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_epsilon": 1e-05,
|
| 27 |
+
"model_type": "mamba",
|
| 28 |
+
"n_layer": 6,
|
| 29 |
+
"num_hidden_layers": 32,
|
| 30 |
+
"pad_token_id": 3,
|
| 31 |
+
"pad_vocab_size_multiple": 8,
|
| 32 |
+
"rescale_prenorm_residual": false,
|
| 33 |
+
"residual_in_fp32": true,
|
| 34 |
+
"rms_norm": true,
|
| 35 |
+
"ssm_cfg": {
|
| 36 |
+
"layer": "Mamba2"
|
| 37 |
+
},
|
| 38 |
+
"state_size": 16,
|
| 39 |
+
"summary_activation": "tanh",
|
| 40 |
+
"summary_first_dropout": 0.4,
|
| 41 |
+
"summary_hidden_size": 128,
|
| 42 |
+
"summary_proj_to_labels": true,
|
| 43 |
+
"summary_type": "cls_index",
|
| 44 |
+
"summary_use_proj": true,
|
| 45 |
+
"tie_embeddings": true,
|
| 46 |
+
"time_step_floor": 0.0001,
|
| 47 |
+
"time_step_init_scheme": "random",
|
| 48 |
+
"time_step_max": 0.1,
|
| 49 |
+
"time_step_min": 0.001,
|
| 50 |
+
"time_step_rank": 48,
|
| 51 |
+
"time_step_scale": 1.0,
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.40.2",
|
| 54 |
+
"use_bias": false,
|
| 55 |
+
"use_cache": true,
|
| 56 |
+
"use_conv_bias": true,
|
| 57 |
+
"vocab_size": 1880
|
| 58 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14f34759aea7318300baaf9a4e1097aaa8735ac6cf622be6fffff0fecdaf7f9c
|
| 3 |
+
size 488581112
|