Add files using upload-large-folder tool

README.md

@@ -1,16 +1,16 @@
----
-license: mit
-pipeline_tag: text-generation
-base_model: deepseek-ai/DeepSeek-V3-0324
-library_name: mlx
-tags:
-- mlx
----
-
-# mlx-community/DeepSeek-V3-0324-4bit
-
-This model [mlx-community/DeepSeek-V3-0324-4bit](https://huggingface.co/mlx-community/DeepSeek-V3-0324-4bit) was
-converted to MLX format from [deepseek-ai/DeepSeek-V3-0324](https://huggingface.co/deepseek-ai/DeepSeek-V3-0324)
+---
+license: mit
+library_name: mlx
+pipeline_tag: text-generation
+base_model: deepseek-ai/DeepSeek-v3-0324
+tags:
+- mlx
+---
+
+# mlx-community/DeepSeek-v3-0324-4bit
+
+This model [mlx-community/DeepSeek-v3-0324-4bit](https://huggingface.co/mlx-community/DeepSeek-v3-0324-4bit) was
+converted to MLX format from [deepseek-ai/DeepSeek-v3-0324](https://huggingface.co/deepseek-ai/DeepSeek-v3-0324)
 using mlx-lm version **0.22.2**.
 
 ## Use with mlx
@@ -22,7 +22,7 @@ pip install mlx-lm
 ```python
 from mlx_lm import load, generate
 
-model, tokenizer = load("mlx-community/DeepSeek-V3-0324-4bit")
+model, tokenizer = load("mlx-community/DeepSeek-v3-0324-4bit")
 
 prompt = "hello"
 

config.json

@@ -9,7 +9,6 @@
         "AutoModel": "modeling_deepseek.DeepseekV3Model",
         "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
     },
-    "aux_loss_alpha": 0.001,
     "bos_token_id": 0,
     "eos_token_id": 1,
     "ep_size": 1,
@@ -32,7 +31,6 @@
     "num_hidden_layers": 61,
     "num_key_value_heads": 128,
     "num_nextn_predict_layers": 1,
-    "pretraining_tp": 1,
     "q_lora_rank": 1536,
     "qk_nope_head_dim": 128,
     "qk_rope_head_dim": 64,
@@ -57,7 +55,6 @@
     "rope_theta": 10000,
     "routed_scaling_factor": 2.5,
     "scoring_func": "sigmoid",
-    "seq_aux": true,
     "tie_word_embeddings": false,
     "topk_group": 4,
     "topk_method": "noaux_tc",

configuration_deepseek.py

@@ -82,11 +82,6 @@ class DeepseekV3Config(PretrainedConfig):
             Beginning of stream token id.
         eos_token_id (`int`, *optional*, defaults to 2):
             End of stream token id.
-        pretraining_tp (`int`, *optional*, defaults to 1):
-            Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this
-            document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is
-            necessary to ensure exact reproducibility of the pretraining results. Please refer to [this
-            issue](https://github.com/pytorch/pytorch/issues/76232).
         tie_word_embeddings (`bool`, *optional*, defaults to `False`):
             Whether to tie weight embeddings
         rope_theta (`float`, *optional*, defaults to 10000.0):
@@ -141,8 +136,6 @@ class DeepseekV3Config(PretrainedConfig):
         first_k_dense_replace = 3,
         norm_topk_prob = True,
         scoring_func = 'sigmoid',
-        aux_loss_alpha = 0.001,
-        seq_aux = True,
         hidden_act="silu",
         max_position_embeddings=4096,
         initializer_range=0.02,
@@ -151,7 +144,6 @@ class DeepseekV3Config(PretrainedConfig):
         pad_token_id=None,
         bos_token_id=0,
         eos_token_id=1,
-        pretraining_tp=1,
         tie_word_embeddings=False,
         rope_theta=10000.0,
         rope_scaling=None,
@@ -184,8 +176,6 @@ class DeepseekV3Config(PretrainedConfig):
         self.first_k_dense_replace = first_k_dense_replace
         self.norm_topk_prob = norm_topk_prob
         self.scoring_func = scoring_func
-        self.aux_loss_alpha = aux_loss_alpha
-        self.seq_aux = seq_aux
         # for backward compatibility
         if num_key_value_heads is None:
             num_key_value_heads = num_attention_heads
@@ -194,7 +184,6 @@ class DeepseekV3Config(PretrainedConfig):
         self.hidden_act = hidden_act
         self.initializer_range = initializer_range
         self.rms_norm_eps = rms_norm_eps
-        self.pretraining_tp = pretraining_tp
         self.use_cache = use_cache
         self.rope_theta = rope_theta
         self.rope_scaling = rope_scaling

model-00001-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420cefc97a209bc7dca275dd0323033580936bae333f040de09259319ee3d6d2
+oid sha256:2c4c331915574139c5ac8dafee748d8fcb3e4c6a960824b98110d9268568cdd2
 size 3725148265

model-00002-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25d56c3409710f0df7596a5e8b084224eeec1a567c5ac87c2889eaef15d78751
-size 4361585379
+oid sha256:4c5255f35ff5eaab3c5b6d5e1d3c184731d66b22b266caaa54b036c8a8d52384
+size 4361585891

model-00003-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cea11170512349c000d6922c83cbcc59c4735a801ee1c51c2f55c22f5af23c9
+oid sha256:3d5a6afc3553763edb09b71c8d5a44ec6075f48a6735d9e396d00b05e2f41e2c
 size 4227859218

model-00004-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee031183293964e596ff4ffcae51847f9a1f8121bca7b03347eab77bebe8d7c0
-size 4361585451
+oid sha256:3cdf53f479116c1171638c721025685020b9548c362af7583689aa4ad69529bb
+size 4361585963

model-00005-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c43bc467be082473d871d806baf8a1e1d866e3a5ec7bb032945047e84c0ec36
-size 4361585389
+oid sha256:3ae6277488338917c5a464d5e8fd5c7c4dbfbe723a62922df203686a43fd7887
+size 4361585901

model-00006-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e3a1a828af5394fd488e47c7e4c61e7bb101bcce14648018ee650bc1e3aaa9
+oid sha256:5825746fe2bc0f8f810efb39ced8a0208d212e95cbf884b8236570ed25cadac6
 size 4227859214

model-00007-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fec87142a75484037bb6892ccaaafe9d94d20dddb78404d5af19e0c0dc970c3
-size 4361585449
+oid sha256:489f16102289544ad7016b6e13e908b96969212f545402c9948af61ab3292e2a
+size 4361585961

model-00008-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10991df4887105b227de9a8a1061d8e23742c46399ad21122fcad4044c9bd1f8
-size 4361585357
+oid sha256:55d2b8c569b90aff3d07f13b5012616ac39d351ad5b981553e8bf93b7ed25897
+size 4361585869

model-00009-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:266eb4800b3c1770d17cdda249d32ebb59a53640cd5bd918859576c7aa7bdf8c
+oid sha256:a88d1c2793b418c78946308827addf2baa9f5697259f855eda505e872b4885f6
 size 4227859218

model-00010-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96f79d5049a4a12fe0d429798d6c5bfb7e2826ab978edef420df076e315bc4f
-size 4361585375
+oid sha256:f6ff44864eda2d49217ca0779d7c08b1da1d1c02c035eb8d78e6114320b63f76
+size 4361585887

model-00011-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:080f4862600e2dbb3039560b6f09ad9df483d98dd6f872a1e1c1c5af34eef2d4
-size 4361585378
+oid sha256:ac186abf0822dece299c4d99ea8230d4a98eaa264def4314acc569e0c7fc4114
+size 4361585890

model-00012-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a5be6328390fb55ffa385bb963ee5de5f7b9414f65fe95ba2953dbf2d08d9a
+oid sha256:4ad58c01b37e2d9334bdf11bf79e5df4cbad9a44c5550b374f5eda094d59e646
 size 4227859224

model-00013-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441c68041831a3c63e7824d20cbae014b7a742572ab2cfd1bf10ad7a63a5e72e
-size 4361585461
+oid sha256:35797d56d5691ff31584924971fd26a87e695b2079f16a7506916422223310a1
+size 4361585973

model-00014-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e5a4209228dff14ab65b23a9738f99acdb18e7fa4e4b50c1a0b87dd6a24c30
-size 4361585391
+oid sha256:fe571eab8db9f37c6ace29d62ae9c92bc419e7494e9373701d6b5751e9da85c0
+size 4361585903

model-00015-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae8a52bf69a23ed355c9580dca55a77f3f04538a8255794bfaef8b7d0ff96e58
+oid sha256:91866b8b087db695b6cc08ef96f6507f7b82e2228d2d095de9c6382bd7997318
 size 4227859224

model-00016-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab6181a065940f73c9bbeec2e9960735734ece3ec3f8a6d522b6c2e7337c435b
-size 4361585455
+oid sha256:edb1becf27c675fdc9eeef2a4822b4f18c2d9b8dd1892d673ee95e391307bcfb
+size 4361585967

model-00017-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e0515fdd973feac7c3cb7ae6d777b8daed28ec872044bfbdbbc4a40a05c55f4
-size 4361585389
+oid sha256:47b49c2748913685fb5b64a916e58b4f0b2024467f63c5a509cf67a3aba14984
+size 4361585901

model-00018-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9719ce5848382650ae4a8aeb66632617b862ddceb921a5774522c650c7bc0412
+oid sha256:4a7f9a5c34b0dedf72a81cc344b1491fa00775971d1cd082f1aeb2a4bcdc87a2
 size 4227859220

model-00019-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5785a9d86fac01fc683c09b53f8b3eabd011e0c598cb15cdc4381e996d798b0a
-size 4361585463
+oid sha256:f683e74041520ce95103eb786e957d957a71fc0274263e5f54f87daca3724f58
+size 4361585975

model-00020-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca66fe3e628db32c083934efd30eeb29464628535bfea25d9e47ac1bece553d
-size 4361585423
+oid sha256:ba991d74f35a7044d83af501fc5bbd1f50f2dd29c3b1a4727ef79d8e99ee414e
+size 4361585935

model-00021-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2894009b4a34c0cf3882c3d386486162f3713c2bb399fd1ed895d7ec27002c35
+oid sha256:5a05a3a2de06fc688c304f31ab3791f6301f1d160bf1d32c2a46decdadc03230
 size 4227859224

model-00022-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380fb312d00798273edecae944448fe553128c3e938f997c53cc5c04c1c08e2a
-size 4361585441
+oid sha256:95c49596dacbf68e4a09cf56f285be0809178c1dc92add3ca9c4deb678ac4e12
+size 4361585953

model-00023-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fb77a4ba2977f0e23edbe7c24b3439ba7d2bd2adbd836905658f38037d745b5
-size 4361585399
+oid sha256:90d574126c1093a287046af5bc9ffb7eaff4209ec249f00a67327ff3352e144e
+size 4361585911

model-00024-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a56cf785ef9cc09c0e2ef65b05d0232fcbfff351d46fce99e3c41a8ebce22652
+oid sha256:1be72c3ef27006fe760f0837c192a4ee7f262fdccd58704fa218c75cd798a6ff
 size 4227859226

model-00025-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e9ec21964726e9d573bb61d7e9263d4b4ee53f2ee2c77d42621f75f2155cf1
-size 4361585485
+oid sha256:82a17d128c561f0e20ac0c749c7b285b7836eb18bd4afb9b9f2abeea47e049e4
+size 4361585997

model-00026-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51453015b22b1f08bb7debc9ff9ebc2cc6be6cb4ccb46c7c73257a06abce16fb
-size 4361585403
+oid sha256:df6f6c06927cf1d039883b27f45b43e9ed94ce9458152806d6582db541430f31
+size 4361585915

model-00027-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddbff7e32eca4c4d17b5f1db7b6c469acdbf43be2107ab45840d68fc750a67e8
+oid sha256:bafa57068931b7351d31402ac953c421fc86a6dc46b9c6e7487826119e77110e
 size 4227859220

model-00028-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b65b05bba4495102a59ded3c52f5f5aded4e502dfafe56700e34b0ebf859f0d6
-size 4361585453
+oid sha256:c15bf7d53d50f173ddf4f747655159e646d1fd22919e42d072d593c79b1aa324
+size 4361585965

model-00029-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e81f9a30da7ed8182741dd13736e34f905a96a6cb2fcd97c52bec63668f537b6
-size 4361585371
+oid sha256:63104e5b296aa062b6cf0aa4f4855c0d6d222795fe3221549e0b9bf8130b023f
+size 4361585883

model-00030-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7facbce0cb6519947195268bd39489c53b9c9c1cb6b22d3ac2315e31d39247bd
+oid sha256:ab19691ee0e93d869c3cf3fb0b6552a4e2e4da12e9c79981621d33d2c98d656e
 size 4227859222

model-00031-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76884c6e1cbf8ae2ec6abe1cc59f6db83e78e1e9a095eb64587c87731790b12b
-size 4361585487
+oid sha256:e99810effc6e15260b83be47276f78f82ca59b518a161666816d3511ea4d0edc
+size 4361585999

model-00032-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:324fc661a86eb6be2e704c2cc0ef37378ac453ddc53967c9d3ce61e50909c8ca
-size 4361585433
+oid sha256:83ba49c6f166f8203d1613530c028005a64f6c9e806930fa405f04a72e775a3f
+size 4361585945

model-00033-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b8a9063ce5d06e4141193a98f206cd8419cfd51a84ede7ca4a756e9d896223
+oid sha256:706d7c0114fa0047413517321bc82eff23b88a2d29b578e43bbe95a2e6b289f2
 size 4227859218

model-00034-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67d2eff1f740301904678fe5d766170db4d4c8d517e85cc6782a06a6be9c677
-size 4361585441
+oid sha256:17b1791bdb04db57b46dbf36770f339eaecaf60c12a8a9d882f5ba0e17ae180e
+size 4361585953

model-00035-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5275be52f00466d3a7639e5b34a47b4e4897fa695c71f4c1c5f23e8ba46bb652
-size 4361585411
+oid sha256:1976a946fd9ca09f3f725cdc877e30a60940a5587a09c4a548a1182d3c5bb7c0
+size 4361585923

model-00036-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9d557b4b7e21d0224cd1ea6d0ba9ab7ff6e5de139321dd3ad3583275579b3bf
+oid sha256:38f3dcbfb878e7cfc3d9d8690448a3a634b38e7e66d047ca96f390a82194d028
 size 4227859224

model-00037-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f3440118ae6f9f417d3bcbebba13f786752ddeec3ea781aa553fc94b9849bc
-size 4361585487
+oid sha256:9d29e442541517efef4895cc8539e85444b714744bcf4adf5ddf3289367897ee
+size 4361585999

model-00038-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deace3371631e6468aca15af2feb48628ebee1c5990d394dcd94038fd06a798a
-size 4361585399
+oid sha256:8a635ae0cc54dd30f6a1380910c37665f3deedae12b2740d32516a0cacf9d36d
+size 4361585911

model-00039-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec3310aa068f5d30e3ee614b7a1d88e004a3bdd393789cb87e8ddef3f93f7c9
+oid sha256:dd60548afce53b3712eccc1031cf3a8f2d70f32c0491b83ad806fd9d71a627e9
 size 4227859220

model-00040-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b999fd7930a1b4b33abffca1a6ded0cdb1c2b3aa6c3eddffb8463e7240165df
-size 4361585427
+oid sha256:3655ad3bb960bcf3b234d590f0b826a85808f237997b82f8b4044a97ba53af7a
+size 4361585939

model-00041-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:712ac11db9b1ff9a33b2ff52ffbe33b292086afb14d014f016d8688ccaf7c708
-size 4361585389
+oid sha256:03811b0e7e10fae0f4bb1930f32856f313f1357cb17b26bef4c0dcfe86ec8784
+size 4361585901

model-00042-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1704dcda42501339d011dc664757788229038fac892e76d53a41a52476872304
+oid sha256:f06f8d344ee0c926ac39a932ec8e1761cfe050216307e909f1d8e76a12faf329
 size 4227859224

model-00043-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1e386a0f57df0a9ee07fd4a2a6acb564dfa0a2fa2470212275c7e23d61b4cb
-size 4361585485
+oid sha256:d2e03f3648d8a8efa1d8690be12fe44b7320f40f366db7513d281be100253831
+size 4361585997

model-00044-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd4888d92d61acadde651e92c2430d490f19be6921c0bd1e4fe9ccaec90294b
-size 4361585425
+oid sha256:9fd06a3592f5a1829ed33de6fab42d3f186480557e007fb99b4f3cca91f4d076
+size 4361585937

model-00045-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b18128aad03c99ca7ff4c968963c46eeb504b815b3a51c9b749e9f0a4f8304c
+oid sha256:2fd10213eac1bbec48311c3046354be068e96e8f7e177db5692210a9aeae7214
 size 4227859224

model-00046-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0817a48bef8ed600c641471784f7edbc63b83f42af1a2c6480febe5b4daa2663
-size 4361585485
+oid sha256:2ff6373a0b3b0b717fa7d0f3fa0a1dbbe7649b8815e928d8a986c488e70bb7e0
+size 4361585997

model-00047-of-00088.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d47e9ad4964efed79547703edfe3af61f76e6bef03aab0f72ad9af9716f01af9
-size 4361585385
+oid sha256:2d1f446ada567bbd8e529c4d13f9e630ae30dcad69b8ff49b11d0aa21346e47e
+size 4361585897