Upload folder using huggingface_hub

README.md

@@ -10,7 +10,7 @@ tags:
 ---
 
 # EZCon/Huihui-Qwen3-VL-4B-Instruct-abliterated-8bit-mlx
-This model was converted to MLX format from [`huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated`]() using mlx-vlm version **0.3.3**.
+This model was converted to MLX format from [`huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated`]() using mlx-vlm version **0.3.4**.
 Refer to the [original model card](https://huggingface.co/huihui-ai/Huihui-Qwen3-VL-4B-Instruct-abliterated) for more details on the model.
 ## Use with mlx
 

config.json

@@ -1,10 +1,50 @@
 {
+    "add_cross_attention": false,
     "architectures": [
         "Qwen3VLForConditionalGeneration"
     ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
     "dtype": "bfloat16",
+    "early_stopping": false,
+    "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,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
     "image_token_id": 151655,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
     "model_type": "qwen3_vl",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "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": {},
     "quantization": {
         "group_size": 64,
         "bits": 8,
@@ -15,23 +55,28 @@
         "bits": 8,
         "mode": "affine"
     },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
     "text_config": {
-        "attention_bias": false,
-        "attention_dropout": 0.0,
-        "bos_token_id": 151643,
-        "dtype": "bfloat16",
-        "eos_token_id": 151645,
-        "head_dim": 128,
-        "hidden_act": "silu",
+        "vocab_size": 151936,
+        "max_position_embeddings": 262144,
         "hidden_size": 2560,
-        "initializer_range": 0.02,
         "intermediate_size": 9728,
-        "max_position_embeddings": 262144,
-        "model_type": "qwen3_vl_text",
-        "num_attention_heads": 32,
         "num_hidden_layers": 36,
+        "num_attention_heads": 32,
         "num_key_value_heads": 8,
+        "head_dim": 128,
+        "hidden_act": "silu",
+        "initializer_range": 0.02,
         "rms_norm_eps": 1e-06,
+        "use_cache": true,
+        "rope_theta": 5000000,
         "rope_scaling": {
             "mrope_interleaved": true,
             "mrope_section": [
@@ -41,34 +86,160 @@
             ],
             "rope_type": "default"
         },
-        "rope_theta": 5000000,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "return_dict": true,
+        "output_hidden_states": false,
+        "torchscript": false,
+        "dtype": "bfloat16",
+        "pruned_heads": {},
         "tie_word_embeddings": true,
-        "use_cache": true,
-        "vocab_size": 151936
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "task_specific_params": null,
+        "problem_type": null,
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": 151643,
+        "pad_token_id": null,
+        "eos_token_id": 151645,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "_name_or_path": "",
+        "model_type": "qwen3_vl_text",
+        "tf_legacy_loss": false,
+        "use_bfloat16": false,
+        "output_attentions": false
     },
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
     "transformers_version": "4.57.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
     "video_token_id": 151656,
     "vision_config": {
-        "deepstack_visual_indexes": [
-            5,
-            11,
-            17
-        ],
-        "depth": 24,
+        "return_dict": true,
+        "output_hidden_states": false,
+        "torchscript": false,
         "dtype": "bfloat16",
-        "hidden_act": "gelu_pytorch_tanh",
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "task_specific_params": null,
+        "problem_type": null,
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "_name_or_path": "",
+        "model_type": "qwen3_vl",
+        "tf_legacy_loss": false,
+        "use_bfloat16": false,
+        "depth": 24,
         "hidden_size": 1024,
-        "in_channels": 3,
-        "initializer_range": 0.02,
+        "hidden_act": "gelu_pytorch_tanh",
         "intermediate_size": 4096,
-        "model_type": "qwen3_vl",
         "num_heads": 16,
-        "num_position_embeddings": 2304,
-        "out_hidden_size": 2560,
+        "in_channels": 3,
         "patch_size": 16,
         "spatial_merge_size": 2,
-        "temporal_patch_size": 2
+        "temporal_patch_size": 2,
+        "out_hidden_size": 2560,
+        "num_position_embeddings": 2304,
+        "initializer_range": 0.02,
+        "deepstack_visual_indexes": [
+            5,
+            11,
+            17
+        ],
+        "output_attentions": false
     },
     "vision_end_token_id": 151653,
     "vision_start_token_id": 151652