initial commit

README.md

@@ -0,0 +1,32 @@
+Stanford Alpaca
+
+FINETUNED USING THE ORIGINAL REPOSITORY: https://github.com/tatsu-lab/stanford_alpaca
+NO LORA HAS BEEN USED
+
+full model 3 epochs og data
+
+CONFIGURATION (default):
+
+```shell
+torchrun --nproc_per_node=4 --master_port=3045 train.py \
+    --model_name_or_path /workspace/llama-7b-hf \
+    --data_path ./alpaca_data.json \
+    --bf16 True \
+    --output_dir /workspace/output \
+    --num_train_epochs 3 \
+    --per_device_train_batch_size 4 \
+    --per_device_eval_batch_size 4 \
+    --gradient_accumulation_steps 8 \
+    --evaluation_strategy "no" \
+    --save_strategy "steps" \
+    --save_steps 200 \
+    --save_total_limit 1 \
+    --learning_rate 2e-5 \
+    --weight_decay 0. \
+    --warmup_ratio 0.03 \
+    --lr_scheduler_type "cosine" \
+    --logging_steps 1 \
+    --fsdp "full_shard auto_wrap" \
+    --fsdp_transformer_layer_cls_to_wrap 'LLaMADecoderLayer' \
+    --tf32 True --report_to="wandb"
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

alpaca7b-4bit.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fbb7f91919b08a203944e4450099f5896c486fb97af3f3b125cc64dcd048d9
+size 4521138824

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "decapoda-research/llama-7b-hf",
+  "architectures": [
+    "LLaMAForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0.dev0"
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "</s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "</s>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "",
+  "eos_token": "",
+  "model_max_length": 512,
+  "padding_side": "right",
+  "special_tokens_map_file": "/home/ubuntu/.cache/huggingface/hub/models--decapoda-research--llama-7b-hf/snapshots/5f98eefcc80e437ef68d457ad7bf167c2c6a1348/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": ""
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e749976892247caff7e8a6860fabeeac4d8b97c8d8a36665746cd35ed5a2bb
+size 3707