Duplicate from tloen/alpaca-lora-7b

Co-authored-by: Eric J. Wang <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,34 @@
+---
+license: mit
+datasets:
+- yahma/alpaca-cleaned
+duplicated_from: tloen/alpaca-lora-7b
+---
+
+This repo contains a low-rank adapter for LLaMA-7b
+fit on the [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) dataset.
+
+This version of the weights was trained with the following hyperparameters:
+
+- Epochs: 10 (load from best epoch)
+- Batch size: 128
+- Cutoff length: 512
+- Learning rate: 3e-4
+- Lora _r_: 16
+- Lora target modules: q_proj, k_proj, v_proj, o_proj
+
+That is:
+
+```
+python finetune.py \
+    --base_model='decapoda-research/llama-7b-hf' \
+    --num_epochs=10 \
+    --cutoff_len=512 \
+    --group_by_length \
+    --output_dir='./lora-alpaca-512-qkvo' \
+    --lora_target_modules='[q_proj,k_proj,v_proj,o_proj]' \
+    --lora_r=16 \
+    --micro_batch_size=8
+```
+
+Instructions for running it can be found at https://github.com/tloen/alpaca-lora.

adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "base_model_name_or_path": "decapoda-research/llama-7b-hf",
+  "bias": "none",
+  "enable_lora": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "merge_weights": false,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e7187f51fbdeff8815046d30f0a325e43491040e6eac8cec5e2ba64f1e87807
+size 67201357