Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,5 @@
-*.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
-*.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
+zephyr-7b-gemma-sft-v0.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-gemma-sft-v0.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-gemma-sft-v0.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-gemma-sft-v0.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+zephyr-7b-gemma-sft-v0.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,77 @@
+---
+license: other
+license_name: gemma-terms-of-use
+license_link: https://ai.google.dev/gemma/terms
+base_model: google/gemma-7b
+tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/deita-10k-v0-sft
+model-index:
+- name: zephyr-7b-gemma-sft
+  results: []
+language:
+- en
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# zephyr-7b-gemma-sft
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the HuggingFaceH4/deita-10k-v0-sft dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9732
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9482        | 1.0   | 299  | 0.9848          |
+| 0.8139        | 2.0   | 599  | 0.9610          |
+| 0.722         | 2.99  | 897  | 0.9732          |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.1

huggingface-metadata.txt

@@ -0,0 +1,9 @@
+url: https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
+branch: main
+download date: 2024-03-01 22:09:44
+sha256sum:
+    10276a0f87e08f62e2829230be70ff541d6e234ffe356ddbf25abeb57433c01b model-00001-of-00004.safetensors
+    ad38dd72c60feb83f5f94b7c637f876a74d27a50fc122da30bf35b3213802a41 model-00002-of-00004.safetensors
+    291250b5d90bd318addab6e1df790bf70cb702814540fbeff26a67d06ee5371c model-00003-of-00004.safetensors
+    809106cf81c8dfa99d1e3e223e42289fc3b51f1227bfdf9070c4fd113858a448 model-00004-of-00004.safetensors
+    22449cb9ef4bad0db7dd93b46ddff7ab7d6a654dd4f903e130ddb6361eac3af5 tokenizer.json

zephyr-7b-gemma-sft-v0.1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c007c6196700d1fbebbd42c3cbd8449a716201451fa1f293b8231bb548101f85
+size 4401867488

zephyr-7b-gemma-sft-v0.1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4618148cb74c4e0f8d495116fb2101169d59e46847c6c0a09805ba067e4e1d10
+size 5127006944

zephyr-7b-gemma-sft-v0.1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9af8f99fe03d289e8c7fa3ad0cc9741e991fb8ed3958d7fe41d2be087051593
+size 6040054496

zephyr-7b-gemma-sft-v0.1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93cf53fc921cbec1fb2f80596b5bc8d19d998b41dea26fe3ffd8077e91a8128
+size 7010167520

zephyr-7b-gemma-sft-v0.1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc567366cd5dab0b6985d06c10a983a292836744d6936cc1c79b8b994f6e7ad0
+size 9077844704