Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Llama-2-7b-hf/.metadata filter=lfs diff=lfs merge=lfs -text
+Llama-2-7b-hf/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+Llama-2-7b-hf/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+Llama-2-7b-hf/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+Llama-2-7b-hf/__0_0.distcp filter=lfs diff=lfs merge=lfs -text

Llama-2-7b-hf/.metadata

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e842139133e778fb3c5e840a6b95ac1e6da912cb86a4fe0c57f0cb4d7335e30
+size 256920

Llama-2-7b-hf/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffcf8c910d072a5027e4623d11661e7ce87244320cd94280329fb8e76ff50ed7
+size 6738791764

Llama-2-7b-hf/__1_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70a6152e37b688d330d7657bb3ce5364b388a3d4cd03486a539be6b3dbbed322
+size 6738791764

Llama-2-7b-hf/__2_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a30ee4e4c8ea4d1b1f326ec98483711dde2ca2f32def134c85a671be194551
+size 6738791764

Llama-2-7b-hf/__3_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75154908cf53670dbe051d6222679d49996909606f8a14b7f6d10ee0cbc2b06e
+size 6738693460

Llama-2-7b-hf/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32004
+}

Llama-2-7b-hf/train_params.yaml

@@ -0,0 +1,57 @@
+add_ctxemb: 'False'
+add_vocab: 'False'
+all_gather: 'true'
+batch_size_training: '16'
+checkpoint_type: StateDictType.SHARDED_STATE_DICT
+clipping_norm: '-1.0'
+compare: 'False'
+cpu_np_head: 'False'
+ctx_proj_layer: 'False'
+ctx_use_peft: 'False'
+dataset: llava_selfrag_single_dataset
+dist_checkpoint_folder: full.prompt_llava.context_mask.with_context.without_sp.key_original_epoch2
+dist_checkpoint_root_folder: /apdcephfs_sh2/share_300000800/user/kaixinma/amylee/RedPajama-Data/img/results
+enable_fsdp: 'True'
+freeze_ctx_encoder: 'False'
+freeze_layers: 'False'
+freeze_question_encoder: 'False'
+from_hf: 'False'
+fsdp_activation_checkpointing: 'True'
+gamma: '0.85'
+load_np_head: 'False'
+low_cpu_fsdp: 'True'
+lr: 2e-05
+memory_bank_length: '0'
+micro_batch_size: '16'
+mixed_precision: 'True'
+model_name: meta-llama/Llama-2-7b-hf
+model_use_peft: 'False'
+natural_form: 'True'
+np_weight: '100.0'
+num_epochs: '3'
+num_freeze_layers: '1'
+num_workers_dataloader: '1'
+one_gpu: 'False'
+optimizer: AdamW
+output_dir: peft_checkpoint
+peft_method: None
+pure_bf16: 'False'
+quantization: 'False'
+question_proj_layer: 'False'
+resume_epoch: '0'
+ret_checkpoint_folder: ''
+ret_first: 'False'
+retriever: ''
+run_validation: 'True'
+save_model: 'True'
+save_optimizer: 'False'
+seed: '2'
+sharding_strategy: ShardingStrategy.FULL_SHARD
+single: 'False'
+target_modules: ''
+token_name: meta-llama/Llama-2-7b-hf
+train: 'True'
+use_fast_kernels: 'False'
+use_fp16: 'False'
+val_batch_size: '1'
+weight_decay: '0.0'