Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2304,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 288256
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

hyperparameters.yaml

@@ -0,0 +1,33 @@
+model_name: google/gemma-2-2b
+out_dir: pretrained_model/models
+precision: bf16-mixed
+initial_checkpoint_dir: google/gemma-2-2b
+resume: false
+data:
+  class_path: litgpt.data.LitData
+  init_args:
+    data_path: data
+    seed: 42
+    num_workers: 8
+train:
+  save_interval: 1000
+  log_interval: 1
+  global_batch_size: 4
+  micro_batch_size: 1
+  lr_warmup_steps: 2000
+  max_tokens: 156800708
+  max_seq_length: 2048
+  tie_embeddings: false
+  max_norm: 1.0
+  min_lr: 4.0e-05
+eval:
+  interval: 1000
+  max_iters: 100
+  initial_validation: false
+  final_validation: true
+optimizer: AdamW
+devices: auto
+num_nodes: 1
+tokenizer_dir: google/gemma-2-2b
+logger_name: tensorboard
+seed: 42

lit_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3727b8adbc7efe76771ec1159e088d170f18710eb326f20f9ba771c58f3e4b61
+size 26822532114

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e57db92ad9a9894fb8e6999c8a4e9cb9aee534e2decba89e5942237d058652
+size 13411292690

model_config.yaml

@@ -0,0 +1,35 @@
+attention_logit_softcapping: 50.0
+attention_scores_scalar: 256
+bias: false
+block_size: 8192
+final_logit_softcapping: 30.0
+gelu_approximate: tanh
+head_size: 256
+hf_config:
+  name: gemma-2-2b
+  org: google
+intermediate_size: 9216
+lm_head_bias: false
+mlp_class_name: GemmaMLP
+n_embd: 2304
+n_expert: 0
+n_expert_per_token: 0
+n_head: 8
+n_layer: 26
+n_query_groups: 4
+name: Gemma-2-2b
+norm_class_name: RMSNorm
+norm_eps: 1.0e-05
+padded_vocab_size: 288256
+padding_multiple: 512
+parallel_residual: false
+post_attention_norm: true
+post_mlp_norm: true
+rope_base: 10000
+rope_condense_ratio: 1
+rotary_percentage: 1.0
+scale_embeddings: true
+shared_attention_norm: false
+sliding_window_layer_placing: 2
+sliding_window_size: 4096
+vocab_size: 288256

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593ff07d6c4160df5d12c5199d4b4d8ea02cac22bf797264db0246a523daea61
+size 4838146