Model save

README.md

@@ -1,3 +1,59 @@
----
-license: mit
----
+---
+license: apache-2.0
+base_model: lmms-lab/llava-onevision-qwen2-7b-ov
+tags:
+- generated_from_trainer
+model-index:
+- name: aha
+  results: []
+library_name: peft
+---
+
+<!-- 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. -->
+
+# aha
+
+This model is a fine-tuned version of [lmms-lab/llava-onevision-qwen2-7b-ov](https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-ov) 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 2
+- total_eval_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.4.0
+- Transformers 4.40.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 2.16.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "lmms-lab/llava-onevision-qwen2-7b-ov",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": [
+    "connector",
+    "mm_projector",
+    "lm_head",
+    "informative_head",
+    "relevance_head",
+    "uncertainty_head"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": "model\\.layers.*(q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)$",
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97060c47ed48e5e64aa43e746949a6fac33f5a78ac80248269322979f04a310
+size 1204788040

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<image>": 151646,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<image>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{{ bos_token + 'system\n' + messages[0]['content'] + eos_token}}{% set messages = messages[1:] %}{% endif %}{% for i in range(messages | length) %}{% set message = messages[i] %}{% if message['role'] == 'user' %}{% if add_stream_query_prompt %}{{ eos_token + '\n' + bos_token + 'user\n' + message['content'] + eos_token }}{% else %}{{ '\n' + bos_token + 'user\n' + message['content'] + eos_token }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '\n' + bos_token + 'assistant\n' + message['content'] + eos_token }}{% elif message['role'] == 'stream' and message['num_frames'] > 0 %}{{ '\n' + bos_token + 'stream\n' + ''.join([49 * '<image>'] * message['num_frames']) + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n' + bos_token + 'assistant\n' }}{% elif add_stream_prompt %}{{ '\n' + bos_token + 'stream\n' }}{% elif add_stream_generation_prompt %}{{ eos_token + '\n' + bos_token + 'assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "LlavaProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd341176c149ec5641fe9dcb2c8115ddbaf4607a19ccacc3e7f55f6c9c56ce49
+size 7544