First model version

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "model_zoo/LLM/mixtral/Mixtral-8x7B-Instruct-v0.1",
+  "architectures": [
+    "LlavaMixtralUniForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "aux_img_fold": false,
+  "aux_with_fpn": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "image_global": false,
+  "image_grid": 1,
+  "image_grid_pinpoints": null,
+  "image_size_aux": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "mm_hidden_size": 1024,
+  "mm_hidden_size_aux": 2880,
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "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": "model_zoo/OpenAI/clip-vit-large-patch14-336",
+  "mm_vision_tower_aux": "model_zoo/OpenAI/openclip-convnext-large-d-320-laion2B-s29B-b131K-ft-soup",
+  "model_type": "llava_uni_mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "optimize_vision_tower": false,
+  "optimize_vision_tower_aux": false,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "tune_mm_mlp_adapter": false,
+  "unified_resampler": "simple_sum",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "use_same_im_pos": false,
+  "video_grid": -1,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674b3ea17c450acaba8c5ae82a5353afdaaa02b336867f0c931be6cd48ea7fa2
+size 4892809584

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db730b04c4a561e5eb5136eb9c6d9b0f26ba3bfea8691598f04d7af743431af
+size 4983004016

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b43bc1316f31731a188fa8aad473f4d639aa5a857d7fbd425c315b20a4334b21
+size 4983004016

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dad6ea8da5307f43eca790fc3cc9bf83ffe2a11dc510bbd1df9249e5b72449b
+size 4899035200

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1efa31efc95ebf0424b7ff198af018b3812a6c210823e7cb3f9d5c5bb9d04038
+size 4983004016

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef2e660731802f0af27ca07e083153641bee69eea73008f87a3884da219102a
+size 4983004016

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b634d8b4446b6d258dfabd3250c82aae28e32a15ca082763e3c0864c3210236
+size 4899035248

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b2229eea12af9e291ad0029a6e77152e6e614d187aae58f9e596d232320973c
+size 4983004072

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106804e7a30f844a5dcb924cd8914034f8479674e70de4f891c73e326c7fe89d
+size 4983004072

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d8260f15e681f4e60c1eafcbe4029e0e4d56897b93faa62c346e4b618a1ddf
+size 4899035248

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e591843df2549a18013517270108d0b230e679ddba5883f8b95c840ff4c3b00d
+size 4983004072

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:009486995e75c3b7daedd0526de95b413975273ccc306237051ed985810639d0
+size 4983004072

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde7c883f3208e75d776d9805bb54cd4f82856fedd64be8ef9064682c455cdc0
+size 4983004072

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e486c25fbf50af7b3af05278388805bcdc19f4a6141dc9682422455d2317c590
+size 4899035248

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3bc5681633e2ac8319d85e8f670620ae4ff796d416809f4304935e3f013a77b
+size 4983004072

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b63e68c1d4ad1912a72dbc470c35e04b59cef7f43832c981e4b9052d2adf8c
+size 4983004072

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76c135be798e3e90dad45d9604fb5ce527243bccd791b9fc2660843e0d13efc
+size 4899035248

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b455c116c8739ab4e5379b698e10f5013b988875e8dcb18408251e41f1bd53b9
+size 4983004072

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56451ae837101e3e61b935a217c956d1e32cddd690c9f4e9cc9d05d9f3a8a143
+size 4967508568

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd944232d7c7ef33e7fbc1eeca8018a2ef7327b3ba3b06fbf57a62ae480c42dc
+size 309635168

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ec025db0c3dd0835865e8181b780e6ef963ff663c9b09361005df2e6af0131
+size 6459