Upload folder using huggingface_hub

hyperparameters.yaml

@@ -0,0 +1,30 @@
+model_name: pythia-160m
+out_dir: out/custom-model
+resume: false
+data:
+  class_path: litgpt.data.TextFiles
+  init_args:
+    train_data_path: train
+    seed: 42
+    num_workers: 4
+train:
+  save_interval: 1000
+  log_interval: 1
+  global_batch_size: 512
+  micro_batch_size: 4
+  lr_warmup_steps: 2000
+  max_tokens: 150000000
+  tie_embeddings: false
+  learning_rate: 0.0004
+  weight_decay: 0.1
+  beta1: 0.9
+  beta2: 0.95
+  max_norm: 1.0
+  min_lr: 4.0e-05
+eval:
+  interval: 1000
+  max_iters: 100
+devices: auto
+tokenizer_dir: checkpoints/EleutherAI/pythia-160m
+logger_name: tensorboard
+seed: 42

lit_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e7f79aa6aff933ec2804c2bc9a67c6d5e85efca5e88cf01b2705953d09a3ad
+size 1948054098

model_config.yaml

@@ -0,0 +1,28 @@
+bias: true
+block_size: 2048
+gelu_approximate: none
+head_size: 64
+hf_config:
+  name: pythia-160m
+  org: EleutherAI
+intermediate_size: 3072
+lm_head_bias: false
+mlp_class_name: GptNeoxMLP
+n_embd: 768
+n_expert: 0
+n_expert_per_token: 0
+n_head: 12
+n_layer: 12
+n_query_groups: 12
+name: pythia-160m
+norm_class_name: LayerNorm
+norm_eps: 1.0e-05
+padded_vocab_size: 50304
+padding_multiple: 128
+parallel_residual: true
+rope_base: 10000
+rope_condense_ratio: 1
+rotary_percentage: 0.25
+scale_embeddings: false
+shared_attention_norm: false
+vocab_size: 50254

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "name_or_path": "EleutherAI/gpt-neox-20b",
+  "special_tokens_map_file": "/admin/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/4e49eadb5d14bd22f314ec3f45b69a87b88c7691/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}