iyashnayi/SocioLens-llama-3.2-3B

README.md

@@ -27,14 +27,14 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yashnayi00-university-of-new-haven/huggingface/runs/2qg27orl) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yashnayi00-university-of-new-haven/huggingface/runs/2501vl5u) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.16.1
+- TRL: 0.17.0
 - Transformers: 4.51.3
 - Pytorch: 2.2.0+cu118
 - Datasets: 3.5.0
@@ -49,7 +49,7 @@ Cite TRL as:
 ```bibtex
 @misc{vonwerra2022trl,
 	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
 	year         = 2020,
 	journal      = {GitHub repository},
 	publisher    = {GitHub},

adapter_config.json

@@ -1,36 +1,23 @@
 {
-  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "meta-llama/Llama-3.2-3B",
   "bias": "none",
-  "corda_config": null,
-  "eva_config": null,
-  "exclude_modules": null,
   "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_bias": false,
   "lora_dropout": 0.15,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 8,
-  "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
     "q_proj",
-    "v_proj"
+    "k_proj",
+    "v_proj",
+    "o_proj"
   ],
-  "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
-  "use_dora": false,
-  "use_rslora": false
+  "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c3be50ee8fbeaeb3e67984c730e276a795074a7c46176ffa70c37f34e226b8d
+oid sha256:0a06de793a88b1b222f1cf6f30c61900be0a23305ab38f5f45a5c28e26955a03
 size 18379784

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd2014c21bd34ab1494eee9ca8bccc38c94b5a65cb51c6169b0081d798ff27f
-size 5624
+oid sha256:471499ea6c127a65719d20d07e813f9600084e7c47fd06805c01fd91f5061315
+size 5688