Hugging Face's logo

unsloth
/
DeepSeek-R1-GGUF

Text Generation
Transformers
GGUF
English
deepseek_v3
deepseek
unsloth
custom_code
Inference Endpoints
conversational
Model card Files Community
14
danielhanchen commited on
Commit
903b67e
·
verified ·
1 Parent(s): 627b496

Add files using upload-large-folder tool

Browse files
Files changed (30) hide show
  1. .gitattributes +20 -0
  2. DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00001-of-00005.gguf +3 -0
  3. DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00002-of-00005.gguf +3 -0
  4. DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00003-of-00005.gguf +3 -0
  5. DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00004-of-00005.gguf +3 -0
  6. DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00005-of-00005.gguf +3 -0
  7. DeepSeek-R1-Q2_K_XS/DeepSeek-R1-Q2_K_XS-00001-of-00005.gguf +2 -2
  8. DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00001-of-00007.gguf +2 -2
  9. DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00002-of-00007.gguf +2 -2
  10. DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00003-of-00007.gguf +2 -2
  11. DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00004-of-00007.gguf +2 -2
  12. DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00005-of-00007.gguf +2 -2
  13. DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00006-of-00007.gguf +2 -2
  14. DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00007-of-00007.gguf +2 -2
  15. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00001-of-00015.gguf +3 -0
  16. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00002-of-00015.gguf +3 -0
  17. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00003-of-00015.gguf +3 -0
  18. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00004-of-00015.gguf +3 -0
  19. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00005-of-00015.gguf +3 -0
  20. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00006-of-00015.gguf +3 -0
  21. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00007-of-00015.gguf +3 -0
  22. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00008-of-00015.gguf +3 -0
  23. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00009-of-00015.gguf +3 -0
  24. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00010-of-00015.gguf +3 -0
  25. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00011-of-00015.gguf +3 -0
  26. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00012-of-00015.gguf +3 -0
  27. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00013-of-00015.gguf +3 -0
  28. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00014-of-00015.gguf +3 -0
  29. DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00015-of-00015.gguf +3 -0
  30. config.json +63 -0
.gitattributes CHANGED
@@ -85,3 +85,23 @@ DeepSeek-R1-Q5_K_M/DeepSeek-R1-Zero-Q5_K_M-00009-of-00010.gguf filter=lfs diff=l
85
  DeepSeek-R1-Q8_0/DeepSeek-R1-BF16-256x20B-Q8_0-00015-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
86
  DeepSeek-R1-Q5_K_M/DeepSeek-R1-Zero-Q5_K_M-00010-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
87
  DeepSeek-R1-Q8_0/DeepSeek-R1-BF16-256x20B-Q8_0-00016-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
  DeepSeek-R1-Q8_0/DeepSeek-R1-BF16-256x20B-Q8_0-00015-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
86
  DeepSeek-R1-Q5_K_M/DeepSeek-R1-Zero-Q5_K_M-00010-of-00010.gguf filter=lfs diff=lfs merge=lfs -text
87
  DeepSeek-R1-Q8_0/DeepSeek-R1-BF16-256x20B-Q8_0-00016-of-00016.gguf filter=lfs diff=lfs merge=lfs -text
88
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00015-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
89
+ DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
90
+ DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
91
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00014-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
92
+ DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
93
+ DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
94
+ DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
95
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00012-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
96
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00006-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
97
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00008-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
98
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00013-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
99
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00011-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
100
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00002-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
101
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00004-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
102
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00009-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
103
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00010-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
104
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00003-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
105
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00005-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
106
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00001-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
107
+ DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00007-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00001-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5719d83f2382a46e0daeac89bb30077ac04cca1800c3d2e64541bac9e1540c9
3
+ size 49369575104
DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00002-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b6169f480fcaf1ddcc0fba88ed4b6ca9753252f768238865b47e3e62f8e96e
3
+ size 48511628064
DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00003-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790e281e676e4b0a07ff03c2cb0ecc0949c843bd22c5cae3ae4dbf46606a2053
3
+ size 48821440768
DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00004-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e774ccf787cdebf256c9796ff46ed9b8240bede2c91b5aa0ecc85a73b06ce8b
3
+ size 48887431840
DeepSeek-R1-Q2_K/DeepSeek-R1-Q2_K-00005-of-00005.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:129bb508d9c9f171ec00c850dd67bf9797c4637ced530546c8b526ce667d9771
3
+ size 48438268160
DeepSeek-R1-Q2_K_XS/DeepSeek-R1-Q2_K_XS-00001-of-00005.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5722d07818c7de1629fc1160a11f71b4b32bffdce29919fa41bc51a881cb0d70
3
- size 49797464960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df8e381870dd3aa2ea20b698f5484a1493fffe5503cae9dd4dcdd6ac56319e6d
3
+ size 49797465088
DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00001-of-00007.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6842c1d166fd8e9cd8652473483d71b45a0f767ad3bb6e1b408e5568e9d41b7
3
- size 45903499488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:566450eed98d0c0e5e9797d9dc6aab7a4c1dde0172a4e709b37db1ff3ed60d26
3
+ size 49654170336
DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00002-of-00007.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7be52863b2af721747de24759ed71f2a016ca78ae6f8efc38a128fd8b8d3771
3
- size 45864735552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0267794ad31155506ed2ea03cc69de1b492840bb7f11cdb3a79ce60ddfbfbc
3
+ size 49210367200
DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00003-of-00007.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d10107f13b4de47b16d1b65e58fff5c6c0a54e19c2bd7adddc03c1fca8ca5f4d
3
- size 46993923776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47965e2c75ce280f205e0b02b5ce23d87cdde15180a5d515a4ba4af52b395b9
3
+ size 49210367200
DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00004-of-00007.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cc34d186d5d69cc916affb5cc00c61717003f8ebcb4a291795d4f49c4365c22
3
- size 45958992096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01bf109ce3063e8a09d1159e35b6e69809cc9181b333acbb7c29c8b9fa23ca76
3
+ size 49210367200
DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00005-of-00007.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dcc60d19901585929718881abef8105fa2709ecda1c300c498bcc2868779e41
3
- size 46993923776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:753e4dad98a94f5ce7911c9d2b239cdd84dcef6632a827e90c84c7f56de176a4
3
+ size 49210367200
DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00006-of-00007.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2df7ab192d77299f5be53b21b7c3c51db3153504bb8476ffa8538e4a4d82326b
3
- size 45958992096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:590eae0dbef97e03dfe1e838835b562e005aac33d30e414769161e05d4d17c19
3
+ size 49210367200
DeepSeek-R1-Q3_K_M/DeepSeek-R1-Q3_K_M-00007-of-00007.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f30665774b0094bec23333262f331f09a48bb7b601434b65c5b3adb56372cea
3
- size 41524328928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e03b23d7132784f2df2b6cc9f24e97e70709683ba483e980961c44d4682172d1
3
+ size 23492389408
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00001-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8917f4d383cdaf65b4a5207de68f0f7d7a7242b5dbe1d2d72897427c81267766
3
+ size 47784554880
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00002-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cca85508c0355e065cd579f084693cebc33d190cd60032293a2517d874c594a
3
+ size 48927727968
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00003-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32e0bc518f441cd21ce94e7303896e8b4bd430855ec7626b1455bd5e522082c5
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00004-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bbd1f3562fed647d42d5899244079172881c48f293d60cdfe2de72774709864
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00005-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d8b8b8ed2e86fafe26eeadb959a7ec3f2f9d380ad6deb3ac84a7205141328b
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00006-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d41b1e6422e8f953cb5a6b4b130283bec07ead34f2dc6b6f8ecb2f6befa62f
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00007-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b847e4a84fa336fe3cd322f886b4fc0b220227a83267cfaa00a337b76b8d4f29
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00008-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69562f3e52af28e8ab5e33d21a830d75b706e6d75dd3ada60b860676ea5b73c
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00009-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4fd8410f84325f13b2f17010c2768e14f5f3052af446d2d1cad35ea02723ae
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00010-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d2561f9bdb0dab22251f50f577868b42b26704456922bd72419cd5c412e0ee3
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00011-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77f3c347655af5468f0b0811ce3dc27bd52b533361ac9990ed4ed2782c2e63a3
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00012-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46bd947333cfc30d8970b60dd6d277ae61c4f9430ed622067624f7304d1979b3
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00013-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1013983bf6c6c10ffe58171ab4adae98cdf689b1f2eaeb7a359f97c6ebfc3104
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00014-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3beb5bca9af86cdafa705bcbe6d3933be423209936be502bab33fe519035237d
3
+ size 48927728000
DeepSeek-R1-Q8_0/DeepSeek-R1.Q8_0-00015-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a0fa68c095156c255eb3b29c056d5936656ebb540c4ed609f3330e8c0a37eb
3
+ size 29441495520
config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_deepseek.DeepseekV3Config",
9
+ "AutoModel": "modeling_deepseek.DeepseekV3Model",
10
+ "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
11
+ },
12
+ "aux_loss_alpha": 0.001,
13
+ "bos_token_id": 0,
14
+ "eos_token_id": 1,
15
+ "ep_size": 1,
16
+ "first_k_dense_replace": 3,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 7168,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 18432,
21
+ "kv_lora_rank": 512,
22
+ "max_position_embeddings": 163840,
23
+ "model_type": "deepseek_v3",
24
+ "moe_intermediate_size": 2048,
25
+ "moe_layer_freq": 1,
26
+ "n_group": 8,
27
+ "n_routed_experts": 256,
28
+ "n_shared_experts": 1,
29
+ "norm_topk_prob": true,
30
+ "num_attention_heads": 128,
31
+ "num_experts_per_tok": 8,
32
+ "num_hidden_layers": 61,
33
+ "num_key_value_heads": 128,
34
+ "num_nextn_predict_layers": 1,
35
+ "pad_token_id": 128815,
36
+ "pretraining_tp": 1,
37
+ "q_lora_rank": 1536,
38
+ "qk_nope_head_dim": 128,
39
+ "qk_rope_head_dim": 64,
40
+ "rms_norm_eps": 1e-06,
41
+ "rope_scaling": {
42
+ "beta_fast": 32,
43
+ "beta_slow": 1,
44
+ "factor": 40,
45
+ "mscale": 1.0,
46
+ "mscale_all_dim": 1.0,
47
+ "original_max_position_embeddings": 4096,
48
+ "type": "yarn"
49
+ },
50
+ "rope_theta": 10000,
51
+ "routed_scaling_factor": 2.5,
52
+ "scoring_func": "sigmoid",
53
+ "seq_aux": true,
54
+ "tie_word_embeddings": false,
55
+ "topk_group": 4,
56
+ "topk_method": "noaux_tc",
57
+ "torch_dtype": "bfloat16",
58
+ "transformers_version": "4.48.1",
59
+ "unsloth_fixed": true,
60
+ "use_cache": true,
61
+ "v_head_dim": 128,
62
+ "vocab_size": 129280
63
+ }