Upload folder using huggingface_hub

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
 library_name: peft
 ---
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 24,
-  "lora_dropout": 0.05,
+  "lora_alpha": 256,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 24,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01dab9a983a8cd337853943020fe8e9582f55a7cbe6bf5cd159e28a1da7f933d
-size 1339739928
+oid sha256:d7a8526970b08dee128ac9d3fbbd82789d52301f27b036e8de7b9c93632be47e
+size 1096962344

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60df18b4e2d6dbf268c69bca29694e364f945a5a054af87abc207f97286975cf
+oid sha256:5c9193c8b0cdf1cc71f0c41fa869dc03bae048f854a526111718806e824b0ebe
 size 5432