Upload folder using huggingface_hub

README.md

@@ -1,11 +1,10 @@
 ---
+license: apache-2.0
+language:
+- en
 base_model:
 - openai/clip-vit-large-patch14-336
 - Qwen/Qwen2-7B
-language:
-- en
-library_name: transformers
-license: apache-2.0
 pipeline_tag: image-text-to-text
 tags:
 - multimodal
@@ -13,10 +12,11 @@ tags:
 - molmo
 - pixmo
 - mlx
+library_name: transformers
 ---
 
 # mlx-community/Molmo-7B-D-0924-6bit
-This model was converted to MLX format from [`allenai/Molmo-7B-D-0924`]() using mlx-vlm version **0.1.0**.
+This model was converted to MLX format from [`allenai/Molmo-7B-D-0924`]() using mlx-vlm version **0.1.7**.
 Refer to the [original model card](https://huggingface.co/allenai/Molmo-7B-D-0924) for more details on the model.
 ## Use with mlx
 

config.json

@@ -1,4 +1,6 @@
 {
+    "_attn_implementation_autoset": false,
+    "add_cross_attention": false,
     "architectures": [
         "MolmoForCausalLM"
     ],
@@ -7,32 +9,87 @@
         "AutoConfig": "config_molmo.MolmoConfig",
         "AutoModelForCausalLM": "modeling_molmo.MolmoForCausalLM"
     },
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
     "clip_qkv": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
     "embedding_size": 152064,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
     "hidden_size": 3584,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
     "initializer_range": 0.02,
     "intermediate_size": 37888,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
     "layer_norm_eps": 1e-06,
     "layer_norm_type": "rms",
+    "length_penalty": 1.0,
+    "max_length": 20,
     "max_position_embeddings": 4096,
+    "min_length": 0,
     "model_type": "molmo",
+    "no_repeat_ngram_size": 0,
     "norm_after": false,
     "num_attention_heads": 28,
+    "num_beam_groups": 1,
+    "num_beams": 1,
     "num_hidden_layers": 28,
     "num_key_value_heads": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
     "qkv_bias": true,
     "quantization": {
         "group_size": 64,
         "bits": 6
     },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
     "rope_theta": 1000000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
     "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
     "torch_dtype": "float32",
-    "transformers_version": "4.43.3",
+    "torchscript": false,
+    "transformers_version": "4.47.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
     "use_cache": true,
     "use_position_ids": true,
     "vision_config": {
-        "intermediate_size": 640
+        "skip_vision_non_divisible": true
     },
     "vocab_size": 152064,
     "weight_tying": false

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e696f353a480bd4d233642ca79eff2b259149452decf30c65a6b91b4080d8f9
+oid sha256:727e5859230507efd23d908791561e335f71dfded2aaf04b86b97be270cba397
 size 5322784718

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35666a6b26463fd28c4ae2c083680b13f248a45ef664f71ef81eabbbd611aad4
-size 1843731045
+oid sha256:dbc7ba5b3adc0baee5e4a44e93d00f9f411c2b0d5d6945d3ae66ae2eeabe0970
+size 1844361571

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
     "metadata": {
-        "total_size": 7166370816
+        "total_size": 7167001600
     },
     "weight_map": {
         "language_model.model.blocks.0.att_proj.bias": "model-00001-of-00002.safetensors",
@@ -455,8 +455,6 @@
         "vision_tower.image_projector.w3.scales": "model-00002-of-00002.safetensors",
         "vision_tower.image_projector.w3.weight": "model-00002-of-00002.safetensors",
         "vision_tower.image_vit.class_embedding": "model-00002-of-00002.safetensors",
-        "vision_tower.image_vit.patch_embedding.biases": "model-00002-of-00002.safetensors",
-        "vision_tower.image_vit.patch_embedding.scales": "model-00002-of-00002.safetensors",
         "vision_tower.image_vit.patch_embedding.weight": "model-00002-of-00002.safetensors",
         "vision_tower.image_vit.positional_embedding": "model-00002-of-00002.safetensors",
         "vision_tower.image_vit.pre_ln.bias": "model-00002-of-00002.safetensors",

tokenizer_config.json

@@ -3843,6 +3843,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "processor_class": "MolmoProcessor",