Training in progress, epoch 0

README.md

@@ -3,16 +3,16 @@ license: apache-2.0
 pipeline_tag: image-text-to-text
 library_name: transformers
 base_model:
-  - OpenGVLab/InternVL3_5-1B-MPO
+- OpenGVLab/InternVL3_5-1B-MPO
 base_model_relation: finetune
 datasets:
-  - OpenGVLab/MMPR-v1.2
-  - OpenGVLab/MMPR-Tiny
+- OpenGVLab/MMPR-v1.2
+- OpenGVLab/MMPR-Tiny
 language:
-  - multilingual
+- multilingual
 tags:
-  - internvl
-  - custom_code
+- internvl
+- custom_code
 ---
 
 # InternVL3_5-1B

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "OpenGVLab/InternVL3_5-1B",
+  "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": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9325329c915a70595f750e6e4bc882902285d1bbaaeb52111f6a3fb6cfe41ad
+size 40428048