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": true,
+  "image_grid": 2,
+  "image_grid_pinpoints": null,
+  "image_size_aux": 1536,
+  "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": 4096,
+  "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:e5beeadee10c7844c6468fa09e37d2992ec88e89e1d25de98457e22d5024d908
+size 4892809584

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dca1b1a78343915384c75418c316e5654a0d23273d8ef05a00d09edbed6d33
+size 4983004016

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc56bf21ecbc7cb56dff180e239d915401ca1095a24b045bc5cf59d9fe65a7f8
+size 4983004016

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81e8317780a043f7557bf00f119b4e6493f33073fc6d88ba363bb13acc86739a
+size 4899035200

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977c82103d1dc3f76b770f39c188d8011e825d72386c7e2acb25a9fe7f5c57a0
+size 4983004016

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954e31d4d8bf4ce634bd5cb73d16d62573ee8036f31f91ff4ac9ef7f9b39ef68
+size 4983004016

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8038edbfa28a95c7abf6750fe81f9b337f5527a55fd2dd9977292ad45fa960a
+size 4899035248

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df4c1913beb41512e038b46d2c1703288eaebb6ab2ff952cfcb6b3bcad2329e
+size 4983004072

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fcf455167fabac92f24adc75608a5201ffc029a632747e138437b822d765f77
+size 4983004072

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a006807baac131627d0cbacb66f69fd92cbcc1d2aa5cdafaf66aed8c647de440
+size 4899035248

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796ba363568dc2204dc04b09049667f6801fe21bb2d3a57ec4198972d0aaec3d
+size 4983004072

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a33be9d0881ec9ff575ab9b3a1214f79814ba7cd06da8419ebf7014cd990c435
+size 4983004072

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de67f5175497a257f936ce3610dd663e88fc21c0c27bc750eeb3f5568352cf59
+size 4983004072

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e735203c952ced739b53e21eea051f4878ba34ead75067eaec64f14869b41b
+size 4899035248

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571b3c848f06fa7381753b2fd4215ef6274ee7e0099e63a09d9f8096e1cbe3c3
+size 4983004072

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e680627e87175d540f3bcd1e7aacb1605bc8b03b5c4c143ba1365fec9af966d1
+size 4983004072

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed19a3840ca79973f387820b1827c5b271248a43da8c9d699c73abfad6fadd10
+size 4899035248

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7cfe9d5f38151366c3f4ab1c214307ae61af098d2d7363f73807ab8230343c
+size 4983004072

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8326a97ef88288f7345a645613611fa8a16177f6c7b6fddbde14d6ed5c789f3
+size 4967508568

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d5a53d6f6353861fc627b607388e906742bb37dbaa4535688bb013c067aa5c
+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": 4096,
+  "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:a0098b6577323ee202a679eb110b70d4f32726992d7dbb6178af1b2a6de5d963
+size 6459