Upload LoRA adapter

README.md

@@ -4,17 +4,17 @@ library_name: transformers
 pipeline_tag: text-generation
 base_model: GSAI-ML/LLaDA-8B-Instruct
 language:
-  - en
+- en
 tags:
-  - llada
-  - tool-calling
-  - lora
-  - peft
-  - function-calling
-  - tools
-  - chatbot
-  - assistant
-  - sft
+- llada
+- tool-calling
+- lora
+- peft
+- function-calling
+- tools
+- chatbot
+- assistant
+- sft
 ---
 
 # LLaDA-8B-Tools

adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "GSAI-ML/LLaDA-8B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_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 sha256:0b12743217bf8dc2a817f06a98accfcce3de288969cec2e19b6eecb167adba1e
+size 402679936