vijayarulmuthu/llama381binstruct_summarize_short

README.md

@@ -20,14 +20,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="VijayAgnel/llama381binstruct_summarize_short", device="cuda")
+generator = pipeline("text-generation", model="vijayarulmuthu/llama381binstruct_summarize_short", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 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/vijayarulmuthu-skyhigh-security/huggingface/runs/7dmmdy7h) 
+[<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/vijayarulmuthu-skyhigh-security/huggingface/runs/fm8xf6wl) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
     "k_proj",
-    "down_proj",
     "up_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
     "gate_proj",
-    "o_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b878a2c5a6c1256f899cc9958cb3fb09416128ea9bbc64c097db62d66cf3c530
+oid sha256:f6dcd9ef2e71b8f6455eaa086d58d13fb4d66e3e9d40b2a199cca6708fc69a93
 size 167832240

runs/Mar25_01-29-17_c28298cabeeb/events.out.tfevents.1742866162.c28298cabeeb.445.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb379360d24b179f5e2d520da26f156867bf59336732d3b0a902b942535ca35
+size 29690

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e203cb55a189a63d5c55efc8245e20fa43c945a64112ba95b1b18fbf3f520916
+oid sha256:90d2b16486e2b0c30480a9e23710313fba76c70913dce977a7fb5d3010aa8545
 size 5688