Add files using upload-large-folder tool

L2L_fineweb-100b_N1.3e08_D2.6e09_C2.1e18/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-100b_N1.3e08_D2.6e09_C2.1e18/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 768,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 12,
+  "n_kv_heads": null,
+  "n_layers": 12,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-100b_N1.6e08_D1.0e10_C1.0e19/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68714bcc90f9e4952a8822852ea121f7bf290e7afc5140096333bdd0012011c5
+size 645127616

L2L_fineweb-100b_N2.7e07_D1.3e09_C2.0e17/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-100b_N2.7e07_D1.3e09_C2.0e17/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 320,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 5,
+  "n_kv_heads": null,
+  "n_layers": 5,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-100b_N3.1e08_D1.2e10_C2.2e19/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-100b_N3.1e08_D1.2e10_C2.2e19/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1088,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 17,
+  "n_kv_heads": null,
+  "n_layers": 17,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-100b_N4.8e08_D1.6e09_C4.6e18/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-100b_N4.8e08_D1.6e09_C4.6e18/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1280,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 20,
+  "n_kv_heads": null,
+  "n_layers": 20,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-edu-100b_N1.1e08_D3.0e08_C2.0e17/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-edu-100b_N1.1e08_D3.0e08_C2.0e17/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 704,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 11,
+  "n_kv_heads": null,
+  "n_layers": 11,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-edu-100b_N1.6e08_D9.9e08_C9.6e17/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-edu-100b_N1.6e08_D9.9e08_C9.6e17/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 832,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 13,
+  "n_kv_heads": null,
+  "n_layers": 13,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-edu-100b_N2.7e07_D1.3e09_C2.0e17/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-edu-100b_N2.7e07_D1.3e09_C2.0e17/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 320,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 5,
+  "n_kv_heads": null,
+  "n_layers": 5,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-edu-100b_N2.7e08_D1.4e10_C2.2e19/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-edu-100b_N2.7e08_D1.4e10_C2.2e19/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1024,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 16,
+  "n_kv_heads": null,
+  "n_layers": 16,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-edu-100b_N2.7e08_D6.2e09_C1.0e19/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa77d6c03c3610ba33d5429ecf17c5ba105fa245752ea3f4f25eb0360035e478
+size 1067730840

L2L_fineweb-edu-100b_N4.2e08_D8.4e08_C2.1e18/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-edu-100b_N4.2e08_D8.4e08_C2.1e18/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1216,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 19,
+  "n_kv_heads": null,
+  "n_layers": 19,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-edu-100b_N4.2e08_D8.8e09_C2.2e19/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-edu-100b_N4.2e08_D8.8e09_C2.2e19/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1216,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 19,
+  "n_kv_heads": null,
+  "n_layers": 19,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-edu-100b_N4.8e08_D3.5e09_C1.0e19/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-edu-100b_N4.8e08_D3.5e09_C1.0e19/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1280,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 20,
+  "n_kv_heads": null,
+  "n_layers": 20,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-edu-100b_N5.8e07_D6.0e09_C2.1e18/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-edu-100b_N5.8e07_D6.0e09_C2.1e18/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 512,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 8,
+  "n_kv_heads": null,
+  "n_layers": 8,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_fineweb-edu-100b_N7.3e07_D4.6e08_C2.0e17/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_fineweb-edu-100b_N7.3e07_D4.6e08_C2.0e17/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 576,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 9,
+  "n_kv_heads": null,
+  "n_layers": 9,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_proof-pile-2_N1.3e08_D2.6e09_C2.1e18/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_proof-pile-2_N1.3e08_D2.6e09_C2.1e18/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 768,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 12,
+  "n_kv_heads": null,
+  "n_layers": 12,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_proof-pile-2_N4.2e08_D8.8e09_C2.2e19/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_proof-pile-2_N4.2e08_D8.8e09_C2.2e19/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1216,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 19,
+  "n_kv_heads": null,
+  "n_layers": 19,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_proof-pile-2_N4.8e08_D7.7e09_C2.2e19/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_proof-pile-2_N4.8e08_D7.7e09_C2.2e19/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1280,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 20,
+  "n_kv_heads": null,
+  "n_layers": 20,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_proof-pile-2_N6.1e08_D1.2e09_C4.6e18/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_proof-pile-2_N6.1e08_D1.2e09_C4.6e18/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1408,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 22,
+  "n_kv_heads": null,
+  "n_layers": 22,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_slimpajama-chunk1_N1.1e08_D3.0e08_C2.0e17/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_slimpajama-chunk1_N1.1e08_D3.0e08_C2.0e17/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 704,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 11,
+  "n_kv_heads": null,
+  "n_layers": 11,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_slimpajama-chunk1_N1.2e09_D6.8e09_C4.8e19/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_slimpajama-chunk1_N1.2e09_D6.8e09_C4.8e19/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1792,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 28,
+  "n_kv_heads": null,
+  "n_layers": 28,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_slimpajama-chunk1_N1.6e08_D1.0e10_C1.0e19/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_slimpajama-chunk1_N1.6e08_D1.0e10_C1.0e19/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 832,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 13,
+  "n_kv_heads": null,
+  "n_layers": 13,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_slimpajama-chunk1_N1.6e08_D2.3e10_C2.2e19/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_slimpajama-chunk1_N1.6e08_D2.3e10_C2.2e19/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 832,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 13,
+  "n_kv_heads": null,
+  "n_layers": 13,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_slimpajama-chunk1_N1.9e08_D8.7e09_C1.0e19/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_slimpajama-chunk1_N1.9e08_D8.7e09_C1.0e19/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 896,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 14,
+  "n_kv_heads": null,
+  "n_layers": 14,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_slimpajama-chunk1_N2.7e08_D2.9e09_C4.6e18/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_slimpajama-chunk1_N2.7e08_D2.9e09_C4.6e18/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1024,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 16,
+  "n_kv_heads": null,
+  "n_layers": 16,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}

L2L_slimpajama-chunk1_N4.2e08_D1.8e09_C4.6e18/README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Library: [More Information Needed]
+- Docs: [More Information Needed]

L2L_slimpajama-chunk1_N4.2e08_D1.8e09_C4.6e18/config.json

@@ -0,0 +1,39 @@
+{
+  "activation_type": "gelu",
+  "alibi": false,
+  "alibi_bias_max": 8.0,
+  "attention_dropout": 0.0,
+  "attention_layer_norm": true,
+  "attention_layer_norm_with_affine": true,
+  "bias_for_layer_norm": false,
+  "block_group_size": 1,
+  "block_type": "sequential",
+  "clip_qkv": null,
+  "d_model": 1216,
+  "embedding_dropout": 0.0,
+  "embedding_size": 32000,
+  "eos_token_id": 2,
+  "flash_attention": false,
+  "include_bias": false,
+  "init_cutoff_factor": null,
+  "init_device": "cpu",
+  "init_fn": "mitchell",
+  "init_std": 0.02,
+  "layer_norm_type": "default",
+  "layer_norm_with_affine": true,
+  "max_sequence_length": 512,
+  "mlp_hidden_size": null,
+  "mlp_ratio": 4,
+  "multi_query_attention": false,
+  "n_heads": 19,
+  "n_kv_heads": null,
+  "n_layers": 19,
+  "pad_token_id": 2,
+  "precision": "amp_bf16",
+  "residual_dropout": 0.0,
+  "rope": true,
+  "rope_full_precision": true,
+  "scale_logits": false,
+  "vocab_size": 32000,
+  "weight_tying": false
+}