Upload model trained with Unsloth

Upload model trained with Unsloth 2x faster

adapter_config.json

@@ -21,7 +21,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0,
   "lora_ga_config": null,
@@ -30,12 +30,12 @@
   "modules_to_save": null,
   "monteclora_config": null,
   "peft_type": "LORA",
-  "peft_version": "0.21.0",
+  "peft_version": "0.21.1",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": "(?:(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:k_proj|q_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|linear|embedding_projection|relative_k_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}(?!.*\\.experts\\.\\d)\\..*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:(?:k_proj|q_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|linear|embedding_projection|relative_k_proj))))|(?:.*?\\baudio_tower\\.(?:.*\\.)?q_proj\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?k_proj\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?v_proj\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?relative_k_proj)|(?:.*?\\baudio_tower\\.(?:.*\\.)?post\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?ffw_layer_1\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?ffw_layer_2\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?linear_start\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?linear_end\\.linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?input_proj_linear)|(?:.*?\\baudio_tower\\.(?:.*\\.)?output_proj)|(?:.*?\\bembed_audio\\.embedding_projection)|(?:.*?\\bembed_vision\\.embedding_projection)|(?:.*?\\bvision_tower\\.patch_embedder\\.input_proj)",
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:k_proj|q_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|linear|embedding_projection|relative_k_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}(?!.*\\.experts\\.\\d)\\..*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:(?:k_proj|q_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|per_layer_input_gate|per_layer_projection|linear|embedding_projection|relative_k_proj)))",
   "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4212d03a67533cad2998d41ec7733d6704467d5583bfde1dab28de7df224d01d
-size 74000832
+oid sha256:dcca073b6540723654b02f3e9c6a78aadab3f87324dcf04a3fa0d7b64944e3fb
+size 101423928