Hailey Schoelkopf
commited on
Commit
·
ce40448
1
Parent(s):
10bec1e
Push to HF hub
Browse files
.gitignore
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
checkpoint-15000/
|
| 2 |
+
events.out.tfevents.1662629254.vesna.257458.2
|
| 3 |
+
checkpoint-5000/
|
| 4 |
+
checkpoint-20000/
|
| 5 |
+
special_tokens_map.json
|
| 6 |
+
eval_results.json
|
| 7 |
+
1662587509.7950025/
|
| 8 |
+
word_embeddings_layernorm.pt
|
| 9 |
+
word_embeddings.pt
|
| 10 |
+
train_results.json
|
| 11 |
+
checkpoint-25000/
|
| 12 |
+
trainer_state.json
|
| 13 |
+
all_results.json
|
| 14 |
+
tokenizer.json
|
| 15 |
+
events.out.tfevents.1662587509.vesna.257458.0
|
| 16 |
+
checkpoint-10000/
|
| 17 |
+
training_args.bin
|
| 18 |
+
tokenizer_config.json
|
oscar_pfeiffer+inv_ru/adapter_config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"adapter_residual_before_ln": false,
|
| 4 |
+
"cross_adapter": false,
|
| 5 |
+
"factorized_phm_W": true,
|
| 6 |
+
"factorized_phm_rule": false,
|
| 7 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
| 8 |
+
"init_weights": "bert",
|
| 9 |
+
"inv_adapter": "nice",
|
| 10 |
+
"inv_adapter_reduction_factor": 2,
|
| 11 |
+
"is_parallel": false,
|
| 12 |
+
"learn_phm": true,
|
| 13 |
+
"leave_out": [],
|
| 14 |
+
"ln_after": false,
|
| 15 |
+
"ln_before": false,
|
| 16 |
+
"mh_adapter": false,
|
| 17 |
+
"non_linearity": "relu",
|
| 18 |
+
"original_ln_after": true,
|
| 19 |
+
"original_ln_before": true,
|
| 20 |
+
"output_adapter": true,
|
| 21 |
+
"phm_bias": true,
|
| 22 |
+
"phm_c_init": "normal",
|
| 23 |
+
"phm_dim": 4,
|
| 24 |
+
"phm_init_range": 0.0001,
|
| 25 |
+
"phm_layer": false,
|
| 26 |
+
"phm_rank": 1,
|
| 27 |
+
"reduction_factor": 16.0,
|
| 28 |
+
"residual_before_ln": true,
|
| 29 |
+
"scaling": 1.0,
|
| 30 |
+
"shared_W_phm": false,
|
| 31 |
+
"shared_phm_rule": true
|
| 32 |
+
},
|
| 33 |
+
"config_id": "dee9800a9d0b30a4",
|
| 34 |
+
"hidden_size": 1024,
|
| 35 |
+
"model_class": "BloomForCausalLM",
|
| 36 |
+
"model_name": "bigscience/bloom-560m",
|
| 37 |
+
"model_type": "bloom",
|
| 38 |
+
"name": "oscar_pfeiffer+inv_ru",
|
| 39 |
+
"version": "3.1.0a0"
|
| 40 |
+
}
|
oscar_pfeiffer+inv_ru/head_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": null,
|
| 3 |
+
"hidden_size": 1024,
|
| 4 |
+
"label2id": {
|
| 5 |
+
"LABEL_0": 0,
|
| 6 |
+
"LABEL_1": 1
|
| 7 |
+
},
|
| 8 |
+
"model_class": "BloomForCausalLM",
|
| 9 |
+
"model_name": "bigscience/bloom-560m",
|
| 10 |
+
"model_type": "bloom",
|
| 11 |
+
"name": null,
|
| 12 |
+
"num_labels": 2,
|
| 13 |
+
"version": "3.1.0a0"
|
| 14 |
+
}
|
oscar_pfeiffer+inv_ru/pytorch_adapter.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea28197196d46bf3fb10df0a7631ebb3f6a5f512e6c0dc5789963bc3894b4e5c
|
| 3 |
+
size 14828209
|
oscar_pfeiffer+inv_ru/pytorch_model_head.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a1df0b611369dd97750fb30f438dc54d8124b89233bc6db01f9f9edceba4c76
|
| 3 |
+
size 1027605227
|