Upload Qwen2VLForConditionalGeneration

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "andrewhinh/qwen2-vl-7b-instruct-full-sft",
+  "base_model_name_or_path": "andrewhinh/qwen2-vl-7b-instruct-lora-sft-merged",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,7 +19,7 @@
   "r": 8,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": "^(?!.*visual).*(?:up_proj|o_proj|v_proj|q_proj|k_proj|down_proj|gate_proj).*",
+  "target_modules": "^(?!.*visual.patch_embed|visual.blocks).*(?:q_proj|k_proj|down_proj|gate_proj|v_proj|o_proj|up_proj).*",
   "task_type": "CAUSAL_LM",
   "use_dora": false,
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea9065b7ba5b5a916e8395b0ef6197f45665e4a04220317801246ba17abdcb70
-size 80792096
+oid sha256:7ce7c858abfdc39ed6d2ee9b516725a5cb008d869661661321673bff7f51d634
+size 40422208

generation_config.json

@@ -1,4 +1,5 @@
 {
+  "attn_implementation": "flash_attention_2",
   "bos_token_id": 151643,
   "do_sample": true,
   "eos_token_id": [
@@ -9,5 +10,5 @@
   "temperature": 0.01,
   "top_k": 1,
   "top_p": 0.001,
-  "transformers_version": "4.46.1"
+  "transformers_version": "4.45.2"
 }