Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+llama-3-8b-spectrum-25.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+llama-3-8b-spectrum-25.bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,67 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+library_name: transformers
+license: llama3
+tags:
+- axolotl
+- generated_from_trainer
+- spectrum finetuning
+- Deepspeed MultiGPU
+- autoquant
+- gguf
+model-index:
+- name: Llama-3-8B-spectrum-25
+  results: []
+---
+
+<!-- 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. -->
+
+
+# Llama-3-8B-spectrum-25
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the [yuvraj17/finetune_alpaca_1K](https://huggingface.co/datasets/yuvraj17/finetune_alpaca_1K) dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2791
+
+## Spectrum Fine-tuning:
+I have used the **Spectrum Fine-tuning** method as described in [Eric Hartford et. al 2024](https://arxiv.org/abs/2406.06623), which selectively targets some ***t%*** of the model layers with the highest **Signal-to-Noise Ratio (SNR)**. By focusing on the most information-dense layers, this approach maximizes fine-tuning efficiency while minimizing compute resources.
+
+**The key goal of Spectrum Fine-tuning is:** *minimize the memory footprint and accelerate LLM training without sacrificing performance.*
+
+The 25% layer selection ensures minimal computational overhead for fine-tuning.
+
+## Training:
+- Trained on **2x A40s (48GB VRAM each)** for over 1 hour using the **Axolotl**.
+
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 2
+
+
+![Train/loss Curve Image](https://cdn-uploads.huggingface.co/production/uploads/66137d95e8d2cda230ddcea6/eSBh0SmeGYYUfx9pKgMIv.png)
+
+![eval/loss Curve Image](https://cdn-uploads.huggingface.co/production/uploads/66137d95e8d2cda230ddcea6/xNslkLH1pKot7tzWtIiu9.png)
+
+
+### Framework versions
+
+- Axolotl 0.4.1
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

llama-3-8b-spectrum-25.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae792bae84df7b4dea2af9b840cc701d237affcdc82fb3d5c49bfabeff51135
+size 4018918432

llama-3-8b-spectrum-25.bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b867950170fd81e415110edb331489f05ec4a37a723effbf052773695b256f
+size 16068891680