Upload folder using huggingface_hub

README.md

@@ -9,11 +9,12 @@ tags:
 - custom_code
 - mlx
 license: mit
+library_name: transformers
 ---
 
 # mlx-community/DeepSeek-OCR-6bit
-This model was converted to MLX format from [`deepseek-ai/DeepSeek-OCR`]() using mlx-vlm version **0.3.5**.
-Refer to the [original model card](https://huggingface.co/deepseek-ai/DeepSeek-OCR) for more details on the model.
+This model was converted to MLX format from [`prince-canuma/DeepSeek-OCR`]() using mlx-vlm version **0.3.10**.
+Refer to the [original model card](https://huggingface.co/prince-canuma/DeepSeek-OCR) for more details on the model.
 ## Use with mlx
 
 ```bash

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if message['role'] == 'user' %}{% elif message['role'] == 'assistant' %}{% endif %}{{message['content']}} {% endfor %}{% if add_generation_prompt %}{% endif %}

config.json

@@ -1,14 +1,11 @@
 {
-    "_attn_implementation_autoset": false,
-    "add_cross_attention": false,
     "architectures": [
         "DeepseekOCRForCausalLM"
     ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "aux_loss_alpha": 0.001,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
+    "auto_map": {
+        "AutoConfig": "modeling_deepseekocr.DeepseekOCRConfig",
+        "AutoModel": "modeling_deepseekocr.DeepseekOCRForCausalLM"
+    },
     "bos_token_id": 0,
     "candidate_resolutions": [
         [
@@ -16,40 +13,21 @@
             1024
         ]
     ],
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 1,
-    "ep_size": 1,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
     "first_k_dense_replace": 1,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
     "global_view_pos": "head",
-    "hidden_act": "silu",
     "hidden_size": 1280,
-    "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-    },
-    "initializer_range": 0.02,
     "intermediate_size": 6848,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
     "kv_lora_rank": null,
-    "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-    },
     "language_config": {
         "architectures": [
             "DeepseekV2ForCausalLM"
         ],
+        "auto_map": {
+            "AutoConfig": "configuration_deepseekv2.DeepseekV2Config",
+            "AutoModel": "modeling_deepseek.DeepseekV2Model",
+            "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
+        },
         "bos_token_id": 0,
         "eos_token_id": 1,
         "first_k_dense_replace": 1,
@@ -77,40 +55,23 @@
         "v_head_dim": 0,
         "vocab_size": 129280
     },
-    "length_penalty": 1.0,
     "lm_head": true,
-    "max_length": 20,
     "max_position_embeddings": 8192,
-    "min_length": 0,
-    "model_type": "DeepseekOCR",
+    "model_type": "deepseekocr",
     "moe_intermediate_size": 896,
-    "moe_layer_freq": 1,
     "n_group": 1,
     "n_routed_experts": 64,
     "n_shared_experts": 2,
-    "no_repeat_ngram_size": 0,
-    "norm_topk_prob": false,
     "num_attention_heads": 10,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_experts_per_tok": 6,
     "num_hidden_layers": 12,
     "num_key_value_heads": 10,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "prefix": null,
-    "pretraining_tp": 1,
-    "problem_type": null,
     "projector_config": {
         "input_dim": 2048,
         "model_type": "mlp_projector",
         "n_embed": 1280,
         "projector_type": "linear"
     },
-    "pruned_heads": {},
     "q_lora_rank": null,
     "qk_nope_head_dim": 0,
     "qk_rope_head_dim": 0,
@@ -124,35 +85,11 @@
         "bits": 6,
         "mode": "affine"
     },
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
     "rm_head": false,
-    "rms_norm_eps": 1e-06,
-    "rope_scaling": null,
-    "rope_theta": 10000.0,
-    "routed_scaling_factor": 1.0,
-    "scoring_func": "softmax",
-    "sep_token_id": null,
-    "seq_aux": true,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
-    "tie_word_embeddings": false,
     "tile_tag": "2D",
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
     "topk_group": 1,
     "topk_method": "greedy",
-    "torchscript": false,
     "transformers_version": "4.46.3",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": true,
     "use_mla": false,
     "v_head_dim": 0,
     "vision_config": {

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a43d9f02d100675c38a78f9f7b042e36008313aea91b3aec78aa66a30e8ce2
-size 3084471389
+oid sha256:e820660fdfd4de509bfa4affad11a34891bd8654055b391f41a0c752daf09073
+size 3185320765