Upload LoRA adapter

README.md

@@ -0,0 +1,31 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen2.5-32B-Instruct
+tags:
+- lora
+- qwen
+- fine-tuned
+library_name: peft
+---
+
+# LoRA Fine-tuned Qwen3-32B
+
+This model is a LoRA fine-tuned version of Qwen2.5-32B-Instruct.
+
+## Training Details
+- Training runtime: 13,587 seconds (3h 46m)
+- Training samples per second: 2.208
+- Final training loss: 0.664
+- Epochs: 1.0
+- Training steps: 1,161
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct")
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-32B-Instruct")
+model = PeftModel.from_pretrained(base_model, "abhayesian/lora-qwen3-32b-docs")
+```

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-32B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ce5a66dac8d6e81381818de03e26b8c148fc275c7c8859ab324f717723dcec
+size 2147605960