Upload TALlavaGemmaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/ib-scratch/chenguang03/vision_share/models/llava-gemma2",
+  "_name_or_path": "google/gemma-2-2b-it",
   "architectures": [
     "TALlavaGemmaForCausalLM"
   ],
@@ -13,27 +13,22 @@
     107
   ],
   "final_logit_softcapping": 30.0,
-  "freeze_mm_mlp_adapter": false,
   "head_dim": 256,
   "hidden_act": "gelu_pytorch_tanh",
   "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 2304,
-  "image_aspect_ratio": "pad",
   "initializer_range": 0.02,
   "intermediate_size": 9216,
   "max_position_embeddings": 8192,
   "mm_hidden_size": 1024,
   "mm_patch_merge_type": "flat",
-  "mm_projector_lr": null,
   "mm_projector_type": "linear",
-  "mm_use_im_patch_token": false,
-  "mm_use_im_start_end": false,
   "mm_vision_select_feature": "patch",
   "mm_vision_select_layer": -2,
   "mm_vision_tower": "openai/clip-vit-large-patch14-336",
   "model_type": "tallava_gemma",
   "num_attention_heads": 8,
-  "num_hidden_layers": 30,
+  "num_hidden_layers": 28,
   "num_key_value_heads": 4,
   "num_learnable_tokens": 32,
   "pad_token_id": 0,
@@ -41,11 +36,8 @@
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
-  "tokenizer_model_max_length": 2048,
-  "tokenizer_padding_side": "right",
   "torch_dtype": "bfloat16",
   "transformers_version": "4.46.2",
-  "tune_mm_mlp_adapter": false,
   "use_cache": true,
   "use_mm_proj": true,
   "vocab_size": 256000

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c1f842c519e70cc2856a88cb106af687d025689afd9bcf7bf0600bc86b4b6dc
+oid sha256:532d792c9178805064170a3ec485b7dedbfccc6fd297b92c31a6091b6c7e41bf
 size 4988025760

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d84b6b81da0513d15f8fef626032bfd684eff1a1e798e4cae5e228f2d03e6dc
-size 1475572040
+oid sha256:4691ff2bc105bdf495169797ba2669ed3705915335fac43ca95c7c9b038dc1fe
+size 1164105176

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 6463497216
+    "total_size": 6152033280
   },
   "weight_map": {
     "model.bottle_neck.text_xattn.input_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -235,28 +235,6 @@
     "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",