Add Ahsan221__Llama-Instruct-8B

Ahsan221__Llama-Instruct-8B/.gitattributes

@@ -0,0 +1,35 @@
+*.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

Ahsan221__Llama-Instruct-8B/README.md

@@ -0,0 +1,96 @@
+---
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+library_name: peft
+license: llama3.1
+tags:
+- generated_from_trainer
+model-index:
+- name: Llama-Instruct-8B
+  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-Instruct-8B
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2981
+
+## 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: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.0291        | 0.1144 | 50   | 1.8063          |
+| 1.3006        | 0.2288 | 100  | 0.6497          |
+| 0.471         | 0.3432 | 150  | 0.4071          |
+| 0.3923        | 0.4577 | 200  | 0.3856          |
+| 0.3784        | 0.5721 | 250  | 0.3746          |
+| 0.3671        | 0.6865 | 300  | 0.3592          |
+| 0.3515        | 0.8009 | 350  | 0.3436          |
+| 0.3334        | 0.9153 | 400  | 0.3328          |
+| 0.3292        | 1.0297 | 450  | 0.3275          |
+| 0.3249        | 1.1442 | 500  | 0.3237          |
+| 0.3213        | 1.2586 | 550  | 0.3215          |
+| 0.3177        | 1.3730 | 600  | 0.3180          |
+| 0.3152        | 1.4874 | 650  | 0.3171          |
+| 0.3141        | 1.6018 | 700  | 0.3142          |
+| 0.3108        | 1.7162 | 750  | 0.3130          |
+| 0.3124        | 1.8307 | 800  | 0.3120          |
+| 0.3112        | 1.9451 | 850  | 0.3104          |
+| 0.3091        | 2.0595 | 900  | 0.3088          |
+| 0.3077        | 2.1739 | 950  | 0.3079          |
+| 0.304         | 2.2883 | 1000 | 0.3065          |
+| 0.3052        | 2.4027 | 1050 | 0.3054          |
+| 0.3017        | 2.5172 | 1100 | 0.3046          |
+| 0.3018        | 2.6316 | 1150 | 0.3039          |
+| 0.3019        | 2.7460 | 1200 | 0.3030          |
+| 0.3017        | 2.8604 | 1250 | 0.3021          |
+| 0.3005        | 2.9748 | 1300 | 0.3017          |
+| 0.2989        | 3.0892 | 1350 | 0.3009          |
+| 0.299         | 3.2037 | 1400 | 0.3007          |
+| 0.2989        | 3.3181 | 1450 | 0.2999          |
+| 0.2978        | 3.4325 | 1500 | 0.2995          |
+| 0.2957        | 3.5469 | 1550 | 0.2993          |
+| 0.2969        | 3.6613 | 1600 | 0.2989          |
+| 0.2961        | 3.7757 | 1650 | 0.2983          |
+| 0.2932        | 3.8902 | 1700 | 0.2981          |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.0.2
+- Tokenizers 0.19.1

Ahsan221__Llama-Instruct-8B/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.02,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

Ahsan221__Llama-Instruct-8B/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66b8feffb7d286b8721afb4caf9cdc4ab1906063bbb33807943cae74ef2e7ac
+size 16785792

Ahsan221__Llama-Instruct-8B/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b926fb86ae289960ffdf3c83daf4da5e62278606535aa0a668932dfc1dca3a10
+size 5240