KempnerInstitute
commited on
Commit
•
f31cd1a
1
Parent(s):
06f980b
Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- L2L_fineweb-100b_N1.1e08_D1.5e10_C1.0e19/README.md +9 -0
- L2L_fineweb-100b_N1.1e08_D1.5e10_C1.0e19/config.json +39 -0
- L2L_fineweb-100b_N1.1e08_D6.6e08_C4.4e17/model.safetensors +3 -0
- L2L_fineweb-100b_N1.3e08_D1.2e09_C9.6e17/model.safetensors +3 -0
- L2L_fineweb-100b_N1.3e08_D1.2e10_C1.0e19/model.safetensors +3 -0
- L2L_fineweb-100b_N2.0e07_D1.7e09_C2.0e17/model.safetensors +3 -0
- L2L_fineweb-100b_N2.3e08_D3.5e10_C4.8e19/model.safetensors +3 -0
- L2L_fineweb-100b_N2.7e08_D2.9e09_C4.6e18/README.md +9 -0
- L2L_fineweb-100b_N2.7e08_D2.9e09_C4.6e18/config.json +39 -0
- L2L_fineweb-100b_N3.5e07_D2.1e09_C4.4e17/model.safetensors +3 -0
- L2L_fineweb-100b_N3.5e07_D9.5e08_C2.0e17/model.safetensors +3 -0
- L2L_fineweb-100b_N3.6e08_D4.6e09_C1.0e19/model.safetensors +3 -0
- L2L_fineweb-100b_N4.2e08_D8.8e09_C2.2e19/model.safetensors +3 -0
- L2L_fineweb-100b_N4.6e07_D3.5e09_C9.6e17/model.safetensors +3 -0
- L2L_fineweb-100b_N4.6e07_D7.7e09_C2.1e18/model.safetensors +3 -0
- L2L_fineweb-100b_N5.8e07_D2.8e09_C9.6e17/model.safetensors +3 -0
- L2L_fineweb-100b_N5.8e07_D6.0e09_C2.1e18/model.safetensors +3 -0
- L2L_fineweb-100b_N7.3e07_D1.0e09_C4.4e17/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N1.1e08_D3.2e09_C2.1e18/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N1.1e08_D6.6e08_C4.4e17/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N1.2e09_D3.1e09_C2.2e19/README.md +9 -0
- L2L_fineweb-edu-100b_N1.2e09_D3.1e09_C2.2e19/config.json +39 -0
- L2L_fineweb-edu-100b_N2.0e07_D1.7e09_C2.0e17/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N2.3e08_D7.3e09_C1.0e19/README.md +9 -0
- L2L_fineweb-edu-100b_N2.3e08_D7.3e09_C1.0e19/config.json +39 -0
- L2L_fineweb-edu-100b_N3.1e08_D2.4e09_C4.6e18/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N3.5e07_D2.1e09_C4.4e17/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N3.6e08_D4.6e09_C1.0e19/README.md +9 -0
- L2L_fineweb-edu-100b_N3.6e08_D4.6e09_C1.0e19/config.json +39 -0
- L2L_fineweb-edu-100b_N4.6e07_D1.6e09_C4.4e17/README.md +9 -0
- L2L_fineweb-edu-100b_N4.6e07_D1.6e09_C4.4e17/config.json +39 -0
- L2L_fineweb-edu-100b_N4.8e08_D1.6e09_C4.6e18/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N5.4e08_D6.8e09_C2.2e19/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N5.8e07_D2.8e09_C9.6e17/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N9.0e07_D1.8e09_C9.6e17/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N9.0e07_D3.7e08_C2.0e17/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N9.0e07_D8.1e08_C4.4e17/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N9.0e07_D8.5e09_C4.6e18/model.safetensors +3 -0
- L2L_proof-pile-2_N1.1e08_D6.6e08_C4.4e17/README.md +9 -0
- L2L_proof-pile-2_N1.1e08_D6.6e08_C4.4e17/config.json +39 -0
- L2L_proof-pile-2_N1.1e08_D6.9e09_C4.6e18/model.safetensors +3 -0
- L2L_proof-pile-2_N1.6e08_D4.5e08_C4.4e17/README.md +9 -0
- L2L_proof-pile-2_N1.6e08_D4.5e08_C4.4e17/config.json +39 -0
- L2L_proof-pile-2_N1.9e08_D4.0e09_C4.6e18/model.safetensors +3 -0
- L2L_proof-pile-2_N2.0e07_D1.7e09_C2.0e17/model.safetensors +3 -0
- L2L_proof-pile-2_N2.3e08_D7.0e08_C9.6e17/model.safetensors +3 -0
- L2L_proof-pile-2_N2.7e08_D3.0e10_C4.8e19/model.safetensors +3 -0
- L2L_proof-pile-2_N2.7e08_D6.2e09_C1.0e19/model.safetensors +3 -0
- L2L_proof-pile-2_N3.5e07_D2.1e09_C4.4e17/model.safetensors +3 -0
- L2L_proof-pile-2_N3.5e07_D4.5e09_C9.6e17/model.safetensors +3 -0
L2L_fineweb-100b_N1.1e08_D1.5e10_C1.0e19/README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- model_hub_mixin
|
4 |
+
- pytorch_model_hub_mixin
|
5 |
+
---
|
6 |
+
|
7 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
8 |
+
- Library: [More Information Needed]
|
9 |
+
- Docs: [More Information Needed]
|
L2L_fineweb-100b_N1.1e08_D1.5e10_C1.0e19/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_type": "gelu",
|
3 |
+
"alibi": false,
|
4 |
+
"alibi_bias_max": 8.0,
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"attention_layer_norm": true,
|
7 |
+
"attention_layer_norm_with_affine": true,
|
8 |
+
"bias_for_layer_norm": false,
|
9 |
+
"block_group_size": 1,
|
10 |
+
"block_type": "sequential",
|
11 |
+
"clip_qkv": null,
|
12 |
+
"d_model": 704,
|
13 |
+
"embedding_dropout": 0.0,
|
14 |
+
"embedding_size": 32000,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"flash_attention": false,
|
17 |
+
"include_bias": false,
|
18 |
+
"init_cutoff_factor": null,
|
19 |
+
"init_device": "cpu",
|
20 |
+
"init_fn": "mitchell",
|
21 |
+
"init_std": 0.02,
|
22 |
+
"layer_norm_type": "default",
|
23 |
+
"layer_norm_with_affine": true,
|
24 |
+
"max_sequence_length": 512,
|
25 |
+
"mlp_hidden_size": null,
|
26 |
+
"mlp_ratio": 4,
|
27 |
+
"multi_query_attention": false,
|
28 |
+
"n_heads": 11,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 11,
|
31 |
+
"pad_token_id": 2,
|
32 |
+
"precision": "amp_bf16",
|
33 |
+
"residual_dropout": 0.0,
|
34 |
+
"rope": true,
|
35 |
+
"rope_full_precision": true,
|
36 |
+
"scale_logits": false,
|
37 |
+
"vocab_size": 32000,
|
38 |
+
"weight_tying": false
|
39 |
+
}
|
L2L_fineweb-100b_N1.1e08_D6.6e08_C4.4e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a083af9fbca68fdf008655c6f2be7b60be6fb355c62644eb9bdc412eaf5c466
|
3 |
+
size 442045664
|
L2L_fineweb-100b_N1.3e08_D1.2e09_C9.6e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e97d4cdb278ec9737499d78eb7ccdb10e980885361366ddd3be0d9e4db03bc70
|
3 |
+
size 536507728
|
L2L_fineweb-100b_N1.3e08_D1.2e10_C1.0e19/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14c0b3bc701dc772378d30faa30e13902b9c2422880ddb5ef64c673b97356c1e
|
3 |
+
size 536507728
|
L2L_fineweb-100b_N2.0e07_D1.7e09_C2.0e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3edc10e17b912ac0023608ad6e42d31e485ff0d328047b3b437fd0e7009295d
|
3 |
+
size 78139936
|
L2L_fineweb-100b_N2.3e08_D3.5e10_C4.8e19/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1295ad3fe74e3918a8fbb9ced691b0e19d2c33f503f5c510cdf7f0d9dd808a8a
|
3 |
+
size 909559448
|
L2L_fineweb-100b_N2.7e08_D2.9e09_C4.6e18/README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- model_hub_mixin
|
4 |
+
- pytorch_model_hub_mixin
|
5 |
+
---
|
6 |
+
|
7 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
8 |
+
- Library: [More Information Needed]
|
9 |
+
- Docs: [More Information Needed]
|
L2L_fineweb-100b_N2.7e08_D2.9e09_C4.6e18/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_type": "gelu",
|
3 |
+
"alibi": false,
|
4 |
+
"alibi_bias_max": 8.0,
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"attention_layer_norm": true,
|
7 |
+
"attention_layer_norm_with_affine": true,
|
8 |
+
"bias_for_layer_norm": false,
|
9 |
+
"block_group_size": 1,
|
10 |
+
"block_type": "sequential",
|
11 |
+
"clip_qkv": null,
|
12 |
+
"d_model": 1024,
|
13 |
+
"embedding_dropout": 0.0,
|
14 |
+
"embedding_size": 32000,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"flash_attention": false,
|
17 |
+
"include_bias": false,
|
18 |
+
"init_cutoff_factor": null,
|
19 |
+
"init_device": "cpu",
|
20 |
+
"init_fn": "mitchell",
|
21 |
+
"init_std": 0.02,
|
22 |
+
"layer_norm_type": "default",
|
23 |
+
"layer_norm_with_affine": true,
|
24 |
+
"max_sequence_length": 512,
|
25 |
+
"mlp_hidden_size": null,
|
26 |
+
"mlp_ratio": 4,
|
27 |
+
"multi_query_attention": false,
|
28 |
+
"n_heads": 16,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 16,
|
31 |
+
"pad_token_id": 2,
|
32 |
+
"precision": "amp_bf16",
|
33 |
+
"residual_dropout": 0.0,
|
34 |
+
"rope": true,
|
35 |
+
"rope_full_precision": true,
|
36 |
+
"scale_logits": false,
|
37 |
+
"vocab_size": 32000,
|
38 |
+
"weight_tying": false
|
39 |
+
}
|
L2L_fineweb-100b_N3.5e07_D2.1e09_C4.4e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbc98d7283b467efd53e18f26074d655533e56622cefd66884924f9cf4b6d031
|
3 |
+
size 140815064
|
L2L_fineweb-100b_N3.5e07_D9.5e08_C2.0e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bedbd3355b1581e0b8b32d8976ead9e8c12a0c990b1057410c3c4add82a869ee
|
3 |
+
size 140815064
|
L2L_fineweb-100b_N3.6e08_D4.6e09_C1.0e19/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f29ed77aedea6e170821127c6345defb9b3c50d938b876ffb89dbadbd0dd7f7
|
3 |
+
size 1441882272
|
L2L_fineweb-100b_N4.2e08_D8.8e09_C2.2e19/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87398fb61e13ac2d56ed7599494851dec76be44808fda390553d8eca870dcbb6
|
3 |
+
size 1660221752
|
L2L_fineweb-100b_N4.6e07_D3.5e09_C9.6e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc9d7ec5af25505d755d26fe40562c9a800e338f577c7966a6eccbfebd92086d
|
3 |
+
size 182182704
|
L2L_fineweb-100b_N4.6e07_D7.7e09_C2.1e18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74f956c29927e288e899fec97a25e2ab30f4d651003f34f399504d8c81376986
|
3 |
+
size 182182704
|
L2L_fineweb-100b_N5.8e07_D2.8e09_C9.6e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:634c3cfdde46da0f18ab94fab128e740575f234415e367ff89f57cdcd4068b22
|
3 |
+
size 231809928
|
L2L_fineweb-100b_N5.8e07_D6.0e09_C2.1e18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:280d3a415ab1f97935a2ebb392163ded1f6fed577321c698f0a57c731584b4c4
|
3 |
+
size 231809928
|
L2L_fineweb-100b_N7.3e07_D1.0e09_C4.4e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7efc8eaef857ee25861f05e473b43c8607ba9ac4b45a9920fb8b2c7601e85195
|
3 |
+
size 290876416
|
L2L_fineweb-edu-100b_N1.1e08_D3.2e09_C2.1e18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a4a988bc760ff3d6c3d692f7c21bfcfc0b30797a56f7fa86a4cba0ad5bef107
|
3 |
+
size 442045664
|
L2L_fineweb-edu-100b_N1.1e08_D6.6e08_C4.4e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe5cfc1322d19a109a365915086a36a816c435bb74ab63026307c8e0fc114db0
|
3 |
+
size 442045664
|
L2L_fineweb-edu-100b_N1.2e09_D3.1e09_C2.2e19/README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- model_hub_mixin
|
4 |
+
- pytorch_model_hub_mixin
|
5 |
+
---
|
6 |
+
|
7 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
8 |
+
- Library: [More Information Needed]
|
9 |
+
- Docs: [More Information Needed]
|
L2L_fineweb-edu-100b_N1.2e09_D3.1e09_C2.2e19/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_type": "gelu",
|
3 |
+
"alibi": false,
|
4 |
+
"alibi_bias_max": 8.0,
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"attention_layer_norm": true,
|
7 |
+
"attention_layer_norm_with_affine": true,
|
8 |
+
"bias_for_layer_norm": false,
|
9 |
+
"block_group_size": 1,
|
10 |
+
"block_type": "sequential",
|
11 |
+
"clip_qkv": null,
|
12 |
+
"d_model": 1792,
|
13 |
+
"embedding_dropout": 0.0,
|
14 |
+
"embedding_size": 32000,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"flash_attention": false,
|
17 |
+
"include_bias": false,
|
18 |
+
"init_cutoff_factor": null,
|
19 |
+
"init_device": "cpu",
|
20 |
+
"init_fn": "mitchell",
|
21 |
+
"init_std": 0.02,
|
22 |
+
"layer_norm_type": "default",
|
23 |
+
"layer_norm_with_affine": true,
|
24 |
+
"max_sequence_length": 512,
|
25 |
+
"mlp_hidden_size": null,
|
26 |
+
"mlp_ratio": 4,
|
27 |
+
"multi_query_attention": false,
|
28 |
+
"n_heads": 28,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 28,
|
31 |
+
"pad_token_id": 2,
|
32 |
+
"precision": "amp_bf16",
|
33 |
+
"residual_dropout": 0.0,
|
34 |
+
"rope": true,
|
35 |
+
"rope_full_precision": true,
|
36 |
+
"scale_logits": false,
|
37 |
+
"vocab_size": 32000,
|
38 |
+
"weight_tying": false
|
39 |
+
}
|
L2L_fineweb-edu-100b_N2.0e07_D1.7e09_C2.0e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7220c66488fa59edc3f0e887472dd5f52ba37743ae4a4cbef5c1b629454d5958
|
3 |
+
size 78139936
|
L2L_fineweb-edu-100b_N2.3e08_D7.3e09_C1.0e19/README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- model_hub_mixin
|
4 |
+
- pytorch_model_hub_mixin
|
5 |
+
---
|
6 |
+
|
7 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
8 |
+
- Library: [More Information Needed]
|
9 |
+
- Docs: [More Information Needed]
|
L2L_fineweb-edu-100b_N2.3e08_D7.3e09_C1.0e19/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_type": "gelu",
|
3 |
+
"alibi": false,
|
4 |
+
"alibi_bias_max": 8.0,
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"attention_layer_norm": true,
|
7 |
+
"attention_layer_norm_with_affine": true,
|
8 |
+
"bias_for_layer_norm": false,
|
9 |
+
"block_group_size": 1,
|
10 |
+
"block_type": "sequential",
|
11 |
+
"clip_qkv": null,
|
12 |
+
"d_model": 960,
|
13 |
+
"embedding_dropout": 0.0,
|
14 |
+
"embedding_size": 32000,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"flash_attention": false,
|
17 |
+
"include_bias": false,
|
18 |
+
"init_cutoff_factor": null,
|
19 |
+
"init_device": "cpu",
|
20 |
+
"init_fn": "mitchell",
|
21 |
+
"init_std": 0.02,
|
22 |
+
"layer_norm_type": "default",
|
23 |
+
"layer_norm_with_affine": true,
|
24 |
+
"max_sequence_length": 512,
|
25 |
+
"mlp_hidden_size": null,
|
26 |
+
"mlp_ratio": 4,
|
27 |
+
"multi_query_attention": false,
|
28 |
+
"n_heads": 15,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 15,
|
31 |
+
"pad_token_id": 2,
|
32 |
+
"precision": "amp_bf16",
|
33 |
+
"residual_dropout": 0.0,
|
34 |
+
"rope": true,
|
35 |
+
"rope_full_precision": true,
|
36 |
+
"scale_logits": false,
|
37 |
+
"vocab_size": 32000,
|
38 |
+
"weight_tying": false
|
39 |
+
}
|
L2L_fineweb-edu-100b_N3.1e08_D2.4e09_C4.6e18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:549b1f9cf3d1a1eb46e1c279960dcb66d72e9715dc8940db032d4828d08f90ff
|
3 |
+
size 1244778504
|
L2L_fineweb-edu-100b_N3.5e07_D2.1e09_C4.4e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8460ee87fee16bd691c50e5ff73cbff58c054b504142d270a22eacd82602adb4
|
3 |
+
size 140815064
|
L2L_fineweb-edu-100b_N3.6e08_D4.6e09_C1.0e19/README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- model_hub_mixin
|
4 |
+
- pytorch_model_hub_mixin
|
5 |
+
---
|
6 |
+
|
7 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
8 |
+
- Library: [More Information Needed]
|
9 |
+
- Docs: [More Information Needed]
|
L2L_fineweb-edu-100b_N3.6e08_D4.6e09_C1.0e19/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_type": "gelu",
|
3 |
+
"alibi": false,
|
4 |
+
"alibi_bias_max": 8.0,
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"attention_layer_norm": true,
|
7 |
+
"attention_layer_norm_with_affine": true,
|
8 |
+
"bias_for_layer_norm": false,
|
9 |
+
"block_group_size": 1,
|
10 |
+
"block_type": "sequential",
|
11 |
+
"clip_qkv": null,
|
12 |
+
"d_model": 1152,
|
13 |
+
"embedding_dropout": 0.0,
|
14 |
+
"embedding_size": 32000,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"flash_attention": false,
|
17 |
+
"include_bias": false,
|
18 |
+
"init_cutoff_factor": null,
|
19 |
+
"init_device": "cpu",
|
20 |
+
"init_fn": "mitchell",
|
21 |
+
"init_std": 0.02,
|
22 |
+
"layer_norm_type": "default",
|
23 |
+
"layer_norm_with_affine": true,
|
24 |
+
"max_sequence_length": 512,
|
25 |
+
"mlp_hidden_size": null,
|
26 |
+
"mlp_ratio": 4,
|
27 |
+
"multi_query_attention": false,
|
28 |
+
"n_heads": 18,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 18,
|
31 |
+
"pad_token_id": 2,
|
32 |
+
"precision": "amp_bf16",
|
33 |
+
"residual_dropout": 0.0,
|
34 |
+
"rope": true,
|
35 |
+
"rope_full_precision": true,
|
36 |
+
"scale_logits": false,
|
37 |
+
"vocab_size": 32000,
|
38 |
+
"weight_tying": false
|
39 |
+
}
|
L2L_fineweb-edu-100b_N4.6e07_D1.6e09_C4.4e17/README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- model_hub_mixin
|
4 |
+
- pytorch_model_hub_mixin
|
5 |
+
---
|
6 |
+
|
7 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
8 |
+
- Library: [More Information Needed]
|
9 |
+
- Docs: [More Information Needed]
|
L2L_fineweb-edu-100b_N4.6e07_D1.6e09_C4.4e17/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_type": "gelu",
|
3 |
+
"alibi": false,
|
4 |
+
"alibi_bias_max": 8.0,
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"attention_layer_norm": true,
|
7 |
+
"attention_layer_norm_with_affine": true,
|
8 |
+
"bias_for_layer_norm": false,
|
9 |
+
"block_group_size": 1,
|
10 |
+
"block_type": "sequential",
|
11 |
+
"clip_qkv": null,
|
12 |
+
"d_model": 448,
|
13 |
+
"embedding_dropout": 0.0,
|
14 |
+
"embedding_size": 32000,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"flash_attention": false,
|
17 |
+
"include_bias": false,
|
18 |
+
"init_cutoff_factor": null,
|
19 |
+
"init_device": "cpu",
|
20 |
+
"init_fn": "mitchell",
|
21 |
+
"init_std": 0.02,
|
22 |
+
"layer_norm_type": "default",
|
23 |
+
"layer_norm_with_affine": true,
|
24 |
+
"max_sequence_length": 512,
|
25 |
+
"mlp_hidden_size": null,
|
26 |
+
"mlp_ratio": 4,
|
27 |
+
"multi_query_attention": false,
|
28 |
+
"n_heads": 7,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 7,
|
31 |
+
"pad_token_id": 2,
|
32 |
+
"precision": "amp_bf16",
|
33 |
+
"residual_dropout": 0.0,
|
34 |
+
"rope": true,
|
35 |
+
"rope_full_precision": true,
|
36 |
+
"scale_logits": false,
|
37 |
+
"vocab_size": 32000,
|
38 |
+
"weight_tying": false
|
39 |
+
}
|
L2L_fineweb-edu-100b_N4.8e08_D1.6e09_C4.6e18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:267c1b6222161e79e074d164ceca4f47119f015fdc1ba5fd3580ca080906bcf8
|
3 |
+
size 1900976584
|
L2L_fineweb-edu-100b_N5.4e08_D6.8e09_C2.2e19/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4a0aa3c1a01080623917027fb862f56b917dc8a9e75130c74bdea8d47faee27
|
3 |
+
size 2165326432
|
L2L_fineweb-edu-100b_N5.8e07_D2.8e09_C9.6e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b42d33b285d3f98c86dd53e9aa332e5a76499999b8ffff38a0f2e29b3c456b08
|
3 |
+
size 231809928
|
L2L_fineweb-edu-100b_N9.0e07_D1.8e09_C9.6e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97b0716dcffb47d06ea19cd6019d690d362f784e041b078a49df764ad97a390b
|
3 |
+
size 360561776
|
L2L_fineweb-edu-100b_N9.0e07_D3.7e08_C2.0e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:363950634745aaedf3d4ffd42ddccf42fcab3710f7a1fcd81f4776da287fdbff
|
3 |
+
size 360561776
|
L2L_fineweb-edu-100b_N9.0e07_D8.1e08_C4.4e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5fefaa58a5a2228997c2785c91dc32828bcb44ce9b9f9c145a7ca5d2e272aaa
|
3 |
+
size 360561776
|
L2L_fineweb-edu-100b_N9.0e07_D8.5e09_C4.6e18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78eebeb0a0cac3224246dd0ea2ff4b122a779b1b1c04c0856e2c310a864d512c
|
3 |
+
size 360561776
|
L2L_proof-pile-2_N1.1e08_D6.6e08_C4.4e17/README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- model_hub_mixin
|
4 |
+
- pytorch_model_hub_mixin
|
5 |
+
---
|
6 |
+
|
7 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
8 |
+
- Library: [More Information Needed]
|
9 |
+
- Docs: [More Information Needed]
|
L2L_proof-pile-2_N1.1e08_D6.6e08_C4.4e17/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_type": "gelu",
|
3 |
+
"alibi": false,
|
4 |
+
"alibi_bias_max": 8.0,
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"attention_layer_norm": true,
|
7 |
+
"attention_layer_norm_with_affine": true,
|
8 |
+
"bias_for_layer_norm": false,
|
9 |
+
"block_group_size": 1,
|
10 |
+
"block_type": "sequential",
|
11 |
+
"clip_qkv": null,
|
12 |
+
"d_model": 704,
|
13 |
+
"embedding_dropout": 0.0,
|
14 |
+
"embedding_size": 32000,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"flash_attention": false,
|
17 |
+
"include_bias": false,
|
18 |
+
"init_cutoff_factor": null,
|
19 |
+
"init_device": "cpu",
|
20 |
+
"init_fn": "mitchell",
|
21 |
+
"init_std": 0.02,
|
22 |
+
"layer_norm_type": "default",
|
23 |
+
"layer_norm_with_affine": true,
|
24 |
+
"max_sequence_length": 512,
|
25 |
+
"mlp_hidden_size": null,
|
26 |
+
"mlp_ratio": 4,
|
27 |
+
"multi_query_attention": false,
|
28 |
+
"n_heads": 11,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 11,
|
31 |
+
"pad_token_id": 2,
|
32 |
+
"precision": "amp_bf16",
|
33 |
+
"residual_dropout": 0.0,
|
34 |
+
"rope": true,
|
35 |
+
"rope_full_precision": true,
|
36 |
+
"scale_logits": false,
|
37 |
+
"vocab_size": 32000,
|
38 |
+
"weight_tying": false
|
39 |
+
}
|
L2L_proof-pile-2_N1.1e08_D6.9e09_C4.6e18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c260c4cd8396de7700df68e82afa1a03391f863d01006de53c439e43d2b3a72
|
3 |
+
size 442045664
|
L2L_proof-pile-2_N1.6e08_D4.5e08_C4.4e17/README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- model_hub_mixin
|
4 |
+
- pytorch_model_hub_mixin
|
5 |
+
---
|
6 |
+
|
7 |
+
This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
|
8 |
+
- Library: [More Information Needed]
|
9 |
+
- Docs: [More Information Needed]
|
L2L_proof-pile-2_N1.6e08_D4.5e08_C4.4e17/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_type": "gelu",
|
3 |
+
"alibi": false,
|
4 |
+
"alibi_bias_max": 8.0,
|
5 |
+
"attention_dropout": 0.0,
|
6 |
+
"attention_layer_norm": true,
|
7 |
+
"attention_layer_norm_with_affine": true,
|
8 |
+
"bias_for_layer_norm": false,
|
9 |
+
"block_group_size": 1,
|
10 |
+
"block_type": "sequential",
|
11 |
+
"clip_qkv": null,
|
12 |
+
"d_model": 832,
|
13 |
+
"embedding_dropout": 0.0,
|
14 |
+
"embedding_size": 32000,
|
15 |
+
"eos_token_id": 2,
|
16 |
+
"flash_attention": false,
|
17 |
+
"include_bias": false,
|
18 |
+
"init_cutoff_factor": null,
|
19 |
+
"init_device": "cpu",
|
20 |
+
"init_fn": "mitchell",
|
21 |
+
"init_std": 0.02,
|
22 |
+
"layer_norm_type": "default",
|
23 |
+
"layer_norm_with_affine": true,
|
24 |
+
"max_sequence_length": 512,
|
25 |
+
"mlp_hidden_size": null,
|
26 |
+
"mlp_ratio": 4,
|
27 |
+
"multi_query_attention": false,
|
28 |
+
"n_heads": 13,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 13,
|
31 |
+
"pad_token_id": 2,
|
32 |
+
"precision": "amp_bf16",
|
33 |
+
"residual_dropout": 0.0,
|
34 |
+
"rope": true,
|
35 |
+
"rope_full_precision": true,
|
36 |
+
"scale_logits": false,
|
37 |
+
"vocab_size": 32000,
|
38 |
+
"weight_tying": false
|
39 |
+
}
|
L2L_proof-pile-2_N1.9e08_D4.0e09_C4.6e18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7106a6f7dd21c88c3a40605d122ab604d7ab3b053659ab0e5b6bcbb7ce423988
|
3 |
+
size 769084968
|
L2L_proof-pile-2_N2.0e07_D1.7e09_C2.0e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba3eb8af1d3e802889d140d0aa83404e2bd523a7f4080f0ab560cfe9bf248a77
|
3 |
+
size 78139936
|
L2L_proof-pile-2_N2.3e08_D7.0e08_C9.6e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd145f1ce6470abdd016d07e54f6cf96da15608f7741dfb42d691cfd393f3774
|
3 |
+
size 909559448
|
L2L_proof-pile-2_N2.7e08_D3.0e10_C4.8e19/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7b72345487d4ca9647f7702338d24845ab66949b8f77d0d9c15e26845388266
|
3 |
+
size 1067730840
|
L2L_proof-pile-2_N2.7e08_D6.2e09_C1.0e19/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48bd8d3e7f7586a34a1560d6fe078f53d38e6c74b9ba67e1f9570fe887441358
|
3 |
+
size 1067730840
|
L2L_proof-pile-2_N3.5e07_D2.1e09_C4.4e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90778d1958fd68b93d81c0d837155feda3c4de8c0f89e807fbb0b634ae29ee20
|
3 |
+
size 140815064
|
L2L_proof-pile-2_N3.5e07_D4.5e09_C9.6e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0c0953b5cd3a1f2bd3dde88b1bc05e4f9bd852eb6e9c377a7c16dd325caeddc
|
3 |
+
size 140815064
|