Idefics3-8B-Llama3-ufo

README.md

@@ -0,0 +1,55 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: HuggingFaceM4/Idefics3-8B-Llama3
+tags:
+- generated_from_trainer
+model-index:
+- name: Idefics3-8B-Llama3-ufo
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Idefics3-8B-Llama3-ufo
+
+This model is a fine-tuned version of [HuggingFaceM4/Idefics3-8B-Llama3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.1
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Idefics3ForConditionalGeneration",
+    "parent_library": "transformers.models.idefics3.modeling_idefics3"
+  },
+  "base_model_name_or_path": "HuggingFaceM4/Idefics3-8B-Llama3",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": true,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4487b99f5b12fd9a4773da17c2eb347017854fad49f34493b3c5fb206ab9aa05
+size 95871944

runs/May09_17-19-35_ip-10-192-12-65/events.out.tfevents.1746811192.ip-10-192-12-65.6870.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6c49deb1e1da855435ef511661a332735163bfeddabe46d0b0e333dda32fec
+size 8551

runs/May09_17-22-11_ip-10-192-12-65/events.out.tfevents.1746811344.ip-10-192-12-65.9564.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78cf9382c1867d62b959282f7388430485b199a487a76734051ca8d7e09dcbc4
+size 8551

runs/May09_17-27-20_ip-10-192-12-65/events.out.tfevents.1746811648.ip-10-192-12-65.14289.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c4aa84fb032d56335aa5f2d8c8b1bc8d105d187f63e67f60302a67a5b169ca4
+size 9339

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6575bbec71dff8bb3cf1344a75b2814fd8ceb450c8b8b2daf519d6c2b336ca4
+size 5368