KempnerInstitute
commited on
Commit
•
3aebd23
1
Parent(s):
dedda12
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_N1.3e08_D5.7e09_C4.6e18/model.safetensors +3 -0
- L2L_fineweb-100b_N1.9e08_D8.3e08_C9.6e17/README.md +9 -0
- L2L_fineweb-100b_N1.9e08_D8.3e08_C9.6e17/config.json +39 -0
- L2L_fineweb-100b_N3.1e08_D5.4e09_C1.0e19/README.md +9 -0
- L2L_fineweb-100b_N3.1e08_D5.4e09_C1.0e19/config.json +39 -0
- L2L_fineweb-100b_N5.4e08_D3.1e09_C1.0e19/README.md +9 -0
- L2L_fineweb-100b_N5.4e08_D3.1e09_C1.0e19/config.json +39 -0
- L2L_fineweb-100b_N5.4e08_D6.8e09_C2.2e19/README.md +9 -0
- L2L_fineweb-100b_N5.4e08_D6.8e09_C2.2e19/config.json +39 -0
- L2L_fineweb-100b_N5.8e07_D5.8e08_C2.0e17/README.md +9 -0
- L2L_fineweb-100b_N5.8e07_D5.8e08_C2.0e17/config.json +39 -0
- L2L_fineweb-100b_N7.3e07_D2.2e09_C9.6e17/README.md +9 -0
- L2L_fineweb-100b_N7.3e07_D2.2e09_C9.6e17/config.json +39 -0
- L2L_fineweb-100b_N7.3e07_D4.8e09_C2.1e18/README.md +9 -0
- L2L_fineweb-100b_N7.3e07_D4.8e09_C2.1e18/config.json +39 -0
- L2L_fineweb-100b_N7.8e08_D2.1e09_C1.0e19/README.md +9 -0
- L2L_fineweb-100b_N7.8e08_D2.1e09_C1.0e19/config.json +39 -0
- L2L_fineweb-100b_N9.0e07_D8.5e09_C4.6e18/README.md +9 -0
- L2L_fineweb-100b_N9.0e07_D8.5e09_C4.6e18/config.json +39 -0
- L2L_fineweb-edu-100b_N1.1e08_D1.4e09_C9.6e17/README.md +9 -0
- L2L_fineweb-edu-100b_N1.1e08_D1.4e09_C9.6e17/config.json +39 -0
- L2L_fineweb-edu-100b_N1.6e08_D4.5e08_C4.4e17/model.safetensors +3 -0
- L2L_fineweb-edu-100b_N1.7e09_D4.6e09_C4.8e19/README.md +9 -0
- L2L_fineweb-edu-100b_N2.7e08_D1.3e09_C2.1e18/README.md +9 -0
- L2L_fineweb-edu-100b_N2.7e08_D1.3e09_C2.1e18/config.json +39 -0
- L2L_fineweb-edu-100b_N4.6e07_D3.5e09_C9.6e17/README.md +9 -0
- L2L_fineweb-edu-100b_N4.6e07_D3.5e09_C9.6e17/config.json +39 -0
- L2L_fineweb-edu-100b_N7.3e07_D1.0e10_C4.6e18/README.md +9 -0
- L2L_fineweb-edu-100b_N7.3e07_D1.0e10_C4.6e18/config.json +39 -0
- L2L_proof-pile-2_N1.3e08_D1.2e10_C1.0e19/README.md +9 -0
- L2L_proof-pile-2_N1.3e08_D1.2e10_C1.0e19/config.json +39 -0
- L2L_proof-pile-2_N1.3e08_D5.7e09_C4.6e18/README.md +9 -0
- L2L_proof-pile-2_N1.3e08_D5.7e09_C4.6e18/config.json +39 -0
- L2L_proof-pile-2_N1.6e08_D1.0e10_C1.0e19/model.safetensors +3 -0
- L2L_proof-pile-2_N1.9e08_D8.3e08_C9.6e17/README.md +9 -0
- L2L_proof-pile-2_N1.9e08_D8.3e08_C9.6e17/config.json +39 -0
- L2L_proof-pile-2_N2.7e08_D1.3e09_C2.1e18/model.safetensors +3 -0
- L2L_proof-pile-2_N2.7e08_D2.9e09_C4.6e18/README.md +9 -0
- L2L_proof-pile-2_N2.7e08_D2.9e09_C4.6e18/config.json +39 -0
- L2L_proof-pile-2_N3.6e08_D9.7e08_C2.1e18/README.md +9 -0
- L2L_proof-pile-2_N3.6e08_D9.7e08_C2.1e18/config.json +39 -0
- L2L_proof-pile-2_N4.6e07_D7.3e08_C2.0e17/model.safetensors +3 -0
- L2L_proof-pile-2_N5.8e07_D1.3e09_C4.4e17/README.md +9 -0
- L2L_proof-pile-2_N5.8e07_D1.3e09_C4.4e17/config.json +39 -0
- L2L_proof-pile-2_N7.3e07_D1.0e09_C4.4e17/README.md +9 -0
- L2L_proof-pile-2_N7.3e07_D1.0e09_C4.4e17/config.json +39 -0
- L2L_proof-pile-2_N7.8e08_D1.0e10_C4.8e19/README.md +9 -0
- L2L_proof-pile-2_N7.8e08_D1.0e10_C4.8e19/config.json +39 -0
- L2L_slimpajama-chunk1_N1.1e08_D1.4e09_C9.6e17/model.safetensors +3 -0
- L2L_slimpajama-chunk1_N2.3e08_D1.5e09_C2.1e18/README.md +9 -0
L2L_fineweb-100b_N1.3e08_D5.7e09_C4.6e18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ff827f642c46a0d26d8c6f3b40a8099f35747167b1937a2bacca1e658bea86b
|
3 |
+
size 536507728
|
L2L_fineweb-100b_N1.9e08_D8.3e08_C9.6e17/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_N1.9e08_D8.3e08_C9.6e17/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": 896,
|
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": 14,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 14,
|
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_N3.1e08_D5.4e09_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_N3.1e08_D5.4e09_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": 1088,
|
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": 17,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 17,
|
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_N5.4e08_D3.1e09_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_N5.4e08_D3.1e09_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": 1344,
|
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": 21,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 21,
|
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_N5.4e08_D6.8e09_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-100b_N5.4e08_D6.8e09_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": 1344,
|
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": 21,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 21,
|
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_N5.8e07_D5.8e08_C2.0e17/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_N5.8e07_D5.8e08_C2.0e17/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": 512,
|
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": 8,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 8,
|
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_N7.3e07_D2.2e09_C9.6e17/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_N7.3e07_D2.2e09_C9.6e17/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": 576,
|
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": 9,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 9,
|
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_N7.3e07_D4.8e09_C2.1e18/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_N7.3e07_D4.8e09_C2.1e18/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": 576,
|
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": 9,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 9,
|
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_N7.8e08_D2.1e09_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_N7.8e08_D2.1e09_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": 1536,
|
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": 24,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 24,
|
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_N9.0e07_D8.5e09_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_N9.0e07_D8.5e09_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": 640,
|
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": 10,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 10,
|
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_N1.1e08_D1.4e09_C9.6e17/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_N1.1e08_D1.4e09_C9.6e17/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-edu-100b_N1.6e08_D4.5e08_C4.4e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b396858be63de39b5a6a5b4c16dc77baa8e3898886ef50e2fd9cd03369f6bced
|
3 |
+
size 645127616
|
L2L_fineweb-edu-100b_N1.7e09_D4.6e09_C4.8e19/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_N2.7e08_D1.3e09_C2.1e18/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_N2.7e08_D1.3e09_C2.1e18/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-edu-100b_N4.6e07_D3.5e09_C9.6e17/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_D3.5e09_C9.6e17/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_N7.3e07_D1.0e10_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-edu-100b_N7.3e07_D1.0e10_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": 576,
|
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": 9,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 9,
|
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_N1.3e08_D1.2e10_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_proof-pile-2_N1.3e08_D1.2e10_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": 768,
|
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": 12,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 12,
|
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_N1.3e08_D5.7e09_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_proof-pile-2_N1.3e08_D5.7e09_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": 768,
|
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": 12,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 12,
|
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_N1.6e08_D1.0e10_C1.0e19/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2d4df0279797a672c746d6ef90a70239cb566fa488b4f7b3201cd23d810ca6d
|
3 |
+
size 645127616
|
L2L_proof-pile-2_N1.9e08_D8.3e08_C9.6e17/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_N1.9e08_D8.3e08_C9.6e17/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": 896,
|
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": 14,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 14,
|
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_N2.7e08_D1.3e09_C2.1e18/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f711c6f5c45967c3b7e33ca30e673737d7a3f77ef68247def823f1bb00f45aa3
|
3 |
+
size 1067730840
|
L2L_proof-pile-2_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_proof-pile-2_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_proof-pile-2_N3.6e08_D9.7e08_C2.1e18/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_N3.6e08_D9.7e08_C2.1e18/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_proof-pile-2_N4.6e07_D7.3e08_C2.0e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5632e8529b9abca32c915d088f7fd8aed4fcf3a8a904523eddbba7ecb5c90af
|
3 |
+
size 182182704
|
L2L_proof-pile-2_N5.8e07_D1.3e09_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_N5.8e07_D1.3e09_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": 512,
|
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": 8,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 8,
|
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_N7.3e07_D1.0e09_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_N7.3e07_D1.0e09_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": 576,
|
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": 9,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 9,
|
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_N7.8e08_D1.0e10_C4.8e19/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_N7.8e08_D1.0e10_C4.8e19/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": 1536,
|
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": 24,
|
29 |
+
"n_kv_heads": null,
|
30 |
+
"n_layers": 24,
|
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_slimpajama-chunk1_N1.1e08_D1.4e09_C9.6e17/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19e06601981f65029df5349fd2dfec59d83bc51c3541ed16dc8c592ea64cec18
|
3 |
+
size 442045664
|
L2L_slimpajama-chunk1_N2.3e08_D1.5e09_C2.1e18/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]
|