Upload folder using huggingface_hub

README.md

@@ -0,0 +1,30 @@
+---
+base_model:
+- Qwen/Qwen2.5-Math-7B
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+library_name: transformers
+tags:
+- mergekit
+- peft
+
+---
+# R1-Qwen-7B-LORA
+
+This is a LoRA extracted from a language model. It was extracted using [mergekit](https://github.com/arcee-ai/mergekit).
+
+## LoRA Details
+
+This LoRA adapter was extracted from [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) and uses [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B) as a base.
+
+### Parameters
+
+The following command was used to extract this LoRA adapter:
+
+```sh
+git clone https://github.com/arcee-ai/mergekit.git
+cd mergekit
+git checkout 9017715655bfc346db0fd1f156f3799084b95b9e
+pip install -e .
+
+mergekit-extract-lora deepseek-ai/DeepSeek-R1-Distill-Qwen-7B Qwen/Qwen2.5-Math-7B OUTPUT_PATH --rank=64
+```

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Math-7B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "post_attention_layernorm",
+    "norm",
+    "input_layernorm"
+  ],
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "lm_head",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "embed_tokens"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045963d1f685bb2950bf65ddf2564f7fe89d36d16a4994d89537cb9d41b689c2
+size 363277008