init repo

.gitattributes

@@ -33,3 +33,4 @@ 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
+model.safetensors filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "out/pretrained_300M_515000",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.1"
+}

hyperparameters.yaml

@@ -0,0 +1,41 @@
+checkpoint_dir: keeeeenw/MicroLlama
+out_dir: out/escho
+devices: 1
+num_nodes: 1
+lora_r: 8
+lora_alpha: 16
+lora_dropout: 0.05
+lora_query: true
+lora_key: false
+lora_value: true
+lora_projection: false
+lora_mlp: false
+lora_head: false
+data:
+  class_path: litgpt.data.JSON
+  init_args:
+    json_path: data/ko_alpaca_data.json
+    mask_prompt: false
+    val_split_fraction: 0.5
+    prompt_style: alpaca
+    ignore_index: -100
+    seed: 42
+    num_workers: 4
+train:
+  save_interval: 1000
+  log_interval: 1
+  global_batch_size: 16
+  micro_batch_size: 1
+  lr_warmup_steps: 100
+  epochs: 5
+  min_lr: 6.0e-05
+eval:
+  interval: 100
+  max_new_tokens: 100
+  max_iters: 100
+  initial_validation: false
+  final_validation: true
+  evaluate_example: first
+optimizer: AdamW
+logger_name: csv
+seed: 1337

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b78e63cb2edadfde3bc32f0b1a9a834d3a78560389360e4b2a5cd3775caed64
+size 609286312

model_config.yaml

@@ -0,0 +1,37 @@
+attention_logit_softcapping: null
+attention_scores_scalar: null
+attn_bias: false
+bias: false
+block_size: 2048
+final_logit_softcapping: null
+gelu_approximate: none
+head_size: 64
+hf_config:
+  name: MicroLlama
+  org: keeeeenw
+intermediate_size: 5632
+lm_head_bias: false
+mlp_class_name: LLaMAMLP
+n_embd: 1024
+n_expert: 0
+n_expert_per_token: 0
+n_head: 16
+n_layer: 12
+n_query_groups: 4
+name: micro-llama-300M
+norm_class_name: RMSNorm
+norm_eps: 1.0e-05
+padded_vocab_size: 32000
+padding_multiple: 64
+parallel_residual: false
+post_attention_norm: false
+post_mlp_norm: false
+rope_adjustments: null
+rope_base: 10000
+rope_condense_ratio: 1
+rotary_percentage: 1.0
+scale_embeddings: false
+shared_attention_norm: false
+sliding_window_layer_placing: null
+sliding_window_size: null
+vocab_size: 32000

prompt_style.yaml

@@ -0,0 +1 @@
+class_path: litgpt.prompts.Alpaca

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}