Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Nhanvi282/stage2-llavaqwen1.5-0.5B-vista-5ep-llama405
+tags:
+- generated_from_trainer
+model-index:
+- name: stage3-moe-ft-llavaqwen1.5-0.5b-vista-5ep_llama405-moe
+  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. -->
+
+# stage3-moe-ft-llavaqwen1.5-0.5b-vista-5ep_llama405-moe
+
+This model is a fine-tuned version of [Nhanvi282/stage2-llavaqwen1.5-0.5B-vista-5ep-llama405](https://huggingface.co/Nhanvi282/stage2-llavaqwen1.5-0.5B-vista-5ep-llama405) 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-06
+- train_batch_size: 4
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 4.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.0.1+cu117
+- Datasets 2.21.0
+- Tokenizers 0.15.1

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|endoftext|>": 151643,
+  "<|extra_0|>": 151646,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "Nhanvi282/stage2-llavaqwen1.5-0.5B-vista-5ep-llama405",
+  "architectures": [
+    "MoELLaVAQwen1_5ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "image_aspect_ratio": "pad",
+  "image_projector_type": "mlp2x_gelu",
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "lora": {},
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "mm_hidden_size": 768,
+  "mm_image_tower": "google/siglip-base-patch16-256-multilingual",
+  "mm_projector_lr": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_video_tower": null,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "model_type": "moe_llava_qwen1_5",
+  "moe": {
+    "capacity_factor": 1.5,
+    "ep_size": 1,
+    "eval_capacity_factor": 2.0,
+    "min_capacity": 0,
+    "moe_enable": true,
+    "moe_layers_idx": [
+      0,
+      2,
+      4,
+      6,
+      8,
+      10,
+      12,
+      14,
+      16,
+      18,
+      20,
+      22
+    ],
+    "moe_mode": "sparse",
+    "num_experts": [
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4
+    ],
+    "router_aux_loss_coef": 0.01,
+    "top_k_experts": 2,
+    "train_modules": [
+      "mlp.gate_proj",
+      "mlp.up_proj",
+      "mlp.down_proj",
+      "wg"
+    ],
+    "use_residual": false
+  },
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pad_token_id": 151646,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.0",
+  "tune_mm_mlp_adapter": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_sliding_window": false,
+  "video_global_proj": false,
+  "video_projector_type": "linear",
+  "video_spatial_proj": false,
+  "video_temproal_proj": false,
+  "vocab_size": 151646
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.37.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f607fe54c24306c6a7dec3b4f870ed2076a1809422be1d7dcd214cddf4b82f
+size 4100964168

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba10297df8814d5413291cb5b89c2042b946b3f127f68a2e2f3fa5bd2ae71d3
+size 1740053129

special_tokens_map.json

@@ -0,0 +1,21 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|extra_0|>",
+  "unk_token": {
+    "content": "<|extra_0|>",
+    "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": "<|extra_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "<|extra_0|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": "<|extra_0|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f53ab8c35916671d7ea7d6ac8b3b1536bf03cee0404ca29fda5addfdd813a9d
+size 5947