Upload folder using huggingface_hub

README.md

@@ -9,7 +9,7 @@ tags:
 ---
 
 # EZCon/RolmOCR-4bit-mlx
-This model was converted to MLX format from [`reducto/RolmOCR`]() using mlx-vlm version **0.1.21**.
+This model was converted to MLX format from [`reducto/RolmOCR`]() using mlx-vlm version **0.1.26**.
 Refer to the [original model card](https://huggingface.co/reducto/RolmOCR) for more details on the model.
 ## Use with mlx
 

config.json

@@ -79,109 +79,14 @@
     "suppress_tokens": null,
     "task_specific_params": null,
     "temperature": 1.0,
-    "text_config": {
-        "vocab_size": 152064,
-        "max_position_embeddings": 128000,
-        "hidden_size": 3584,
-        "intermediate_size": 18944,
-        "num_hidden_layers": 28,
-        "num_attention_heads": 28,
-        "use_sliding_window": false,
-        "sliding_window": 32768,
-        "max_window_layers": 28,
-        "num_key_value_heads": 4,
-        "hidden_act": "silu",
-        "initializer_range": 0.02,
-        "rms_norm_eps": 1e-06,
-        "use_cache": false,
-        "rope_theta": 1000000.0,
-        "attention_dropout": 0.0,
-        "rope_scaling": {
-            "mrope_section": [
-                16,
-                24,
-                24
-            ],
-            "rope_type": "default",
-            "type": "default"
-        },
-        "return_dict": true,
-        "output_hidden_states": false,
-        "output_attentions": false,
-        "torchscript": false,
-        "torch_dtype": "bfloat16",
-        "use_bfloat16": false,
-        "tf_legacy_loss": false,
-        "pruned_heads": {},
-        "tie_word_embeddings": false,
-        "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,
-        "max_length": 20,
-        "min_length": 0,
-        "do_sample": false,
-        "early_stopping": false,
-        "num_beams": 1,
-        "num_beam_groups": 1,
-        "diversity_penalty": 0.0,
-        "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,
-        "architectures": [
-            "Qwen2_5_VLForConditionalGeneration"
-        ],
-        "finetuning_task": null,
-        "id2label": {
-            "0": "LABEL_0",
-            "1": "LABEL_1"
-        },
-        "label2id": {
-            "LABEL_0": 0,
-            "LABEL_1": 1
-        },
-        "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,
-        "task_specific_params": null,
-        "problem_type": null,
-        "_name_or_path": "",
-        "_attn_implementation_autoset": false,
-        "model_type": "qwen2_5_vl_text",
-        "vision_end_token_id": 151653,
-        "vision_start_token_id": 151652,
-        "vision_token_id": 151654
-    },
     "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
     "tie_word_embeddings": false,
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": "bfloat16",
     "torchscript": false,
-    "transformers_version": "4.52.0.dev0",
+    "transformers_version": "4.51.3",
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": false,
@@ -269,8 +174,7 @@
             23,
             31
         ],
-        "out_hidden_size": 3584,
-        "initializer_range": 0.02
+        "out_hidden_size": 3584
     },
     "vision_end_token_id": 151653,
     "vision_start_token_id": 151652,

tokenizer_config.json

@@ -195,6 +195,7 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",