Upload model

README.md

@@ -0,0 +1,19 @@
+---
+base_model: deepseek-ai/deepseek-coder-1.3b-instruct_raw
+library_name: peft
+---
+
+# Model Card for Model ID
+
+This model is trained to provide modified cv model implementations in the LEMUR dataset project to extend the dataset.
+
+## Model Details
+
+### Model Description
+
+The model can change parameters or layers when asked to improve the implementation of provided codes from the LEMUR project. The answer should only contain codes without explanations, even if it is not required to do so in the prompt. The model should respond codes with methods concerning the requirements of the LEMUR dataset. For most codes with average implementation complexity, at least one change should be guaranteed.
+
+- **Model type:** Peft Model
+- **Language(s):** English
+- **License:** MIT
+- **Finetuned from model [optional]:** deepseek-coder-1.3b-instruct_raw

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct_raw",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": true,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a29fc297e9903d6eac45df051eea0f83fa8f801874076f986f8fdfa0765688
+size 241970040