EdBerg/SmolLM2-1.7B-Instruct_Baha_1

README.md

@@ -27,7 +27,7 @@ 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/harpermia882/huggingface/runs/4kdpchsk)
+[<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/harpermia882/huggingface/runs/7sqm3t5e)
 
 This model was trained with SFT.
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6abf08d52d0b16874c6e34ca8a2db14d2f78e355cd3fb43d58d2987260673905
+oid sha256:484e4e948c02983a58cded42ea05c3381c54c09f6dd3112324a1f69b5dce4bb5
 size 36220072

runs/Feb13_15-58-41_66bb6d3c0a51/events.out.tfevents.1739462323.66bb6d3c0a51.265.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a73273468b2d569591ae02808af39fc192c6bb38163832eeef52f8090fb901
+size 849976

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104a4a0f1675518101c2be1f8a1b916ae0e6573b73c5556dd411a17374deca39
+oid sha256:a542eb58d1ba3709202a8021d62d633c9af6ad83f2b59c9307fd9e17de490a35
 size 5624