Upload 11 files

README.md

@@ -0,0 +1,24 @@
+---
+language:
+- en
+tags:
+- mlx
+datasets:
+- liuhaotian/LLaVA-Instruct-150K
+pipeline_tag: image-to-text
+inference: false
+arxiv: 2304.08485
+---
+
+# mlx-community/llava-1.5-7b-8bit
+This model was converted to MLX format from [`llava-hf/llava-1.5-7b-hf`]() using mlx-vlm version **0.0.4**.
+Refer to the [original model card](https://huggingface.co/llava-hf/llava-1.5-7b-hf) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+```
+
+```bash
+python -m mlx_vlm.generate --model mlx-community/llava-1.5-7b-8bit --max-tokens 100 --temp 0.0
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

config.json

@@ -0,0 +1,42 @@
+{
+    "architectures": [
+        "LlavaForConditionalGeneration"
+    ],
+    "ignore_index": -100,
+    "image_token_index": 32000,
+    "model_type": "llava",
+    "pad_token_id": 32001,
+    "projector_hidden_act": "gelu",
+    "quantization": {
+        "group_size": 64,
+        "bits": 8
+    },
+    "text_config": {
+        "_name_or_path": "lmsys/vicuna-7b-v1.5",
+        "architectures": [
+            "LlamaForCausalLM"
+        ],
+        "max_position_embeddings": 4096,
+        "model_type": "llama",
+        "rms_norm_eps": 1e-05,
+        "torch_dtype": "float16",
+        "vocab_size": 32064
+    },
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.36.0.dev0",
+    "vision_config": {
+        "hidden_size": 1024,
+        "image_size": 336,
+        "intermediate_size": 4096,
+        "model_type": "clip_vision_model",
+        "num_attention_heads": 16,
+        "num_hidden_layers": 24,
+        "patch_size": 14,
+        "projection_dim": 768,
+        "vocab_size": 32000
+    },
+    "vision_feature_layer": -2,
+    "vision_feature_select_strategy": "default",
+    "vocab_size": 32064
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c37dc0a1f864cfa98841dd2a0280852f4cc5ad3bbdc0db8b7228e8a07e052d
+size 5361046621

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9951a0bc9673a130b08b655b4f0ca1b5c5bd3dd5855278d5ae9f77caf980488
+size 2145161125

preprocessor_config.json

@@ -0,0 +1,45 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_center_crop",
+    "crop_size",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "do_convert_rgb",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_size": {
+    "height": 336,
+    "width": 336
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 336
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}