Upload 10 files

README.md

@@ -11,7 +11,7 @@ arxiv: 2304.08485
 ---
 
 # mlx-community/llava-1.5-7b-4bit
-This model was converted to MLX format from [`llava-hf/llava-1.5-7b-hf`]() using mlx-vllm version **0.0.3**.
+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
 
@@ -20,8 +20,5 @@ pip install -U mlx-vlm
 ```
 
 ```bash
-python -m mlx_vlm.generate --model mlx-community/llava-1.5-7b-4bit \
---prompt "what are these?" --image "http://images.cocodataset.org/val2017/000000039769.jpg" \
---max-tokens 100 --temp 0.0 
+python -m mlx_vlm.generate --model mlx-community/llava-1.5-7b-4bit --max-tokens 100 --temp 0.0
 ```
-

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0fbefdb9259abf4a2a438a057eaafa437d1b057f4b5b605b9211ba39ed8d237
-size 4164736149
+oid sha256:13c021a1fad60c7fcd9e3f3ff1c7150fbe6a595151b5d5e979dbdb0122586ae8
+size 3975094479

model.safetensors.index.json

@@ -1,11 +1,13 @@
 {
     "metadata": {
-        "total_size": 4164546560
+        "total_size": 3974904384
     },
     "weight_map": {
         "language_model.lm_head.biases": "model.safetensors",
         "language_model.lm_head.scales": "model.safetensors",
         "language_model.lm_head.weight": "model.safetensors",
+        "language_model.model.embed_tokens.biases": "model.safetensors",
+        "language_model.model.embed_tokens.scales": "model.safetensors",
         "language_model.model.embed_tokens.weight": "model.safetensors",
         "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
         "language_model.model.layers.0.mlp.down_proj.biases": "model.safetensors",
@@ -754,6 +756,8 @@
         "multi_modal_projector.linear_2.weight": "model.safetensors",
         "vision_tower.vision_model.embeddings.class_embedding": "model.safetensors",
         "vision_tower.vision_model.embeddings.patch_embedding.weight": "model.safetensors",
+        "vision_tower.vision_model.embeddings.position_embedding.biases": "model.safetensors",
+        "vision_tower.vision_model.embeddings.position_embedding.scales": "model.safetensors",
         "vision_tower.vision_model.embeddings.position_embedding.weight": "model.safetensors",
         "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
         "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",

tokenizer.json

@@ -152,6 +152,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json

@@ -46,7 +46,6 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "padding_side": "left",