danielhanchen commited on
Commit
54fe4d9
·
verified ·
1 Parent(s): a86bcb6

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Q8_0/MAI-DS-R1-Q8_0-00004-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Q8_0/MAI-DS-R1-Q8_0-00001-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Q8_0/MAI-DS-R1-Q8_0-00005-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Q8_0/MAI-DS-R1-Q8_0-00003-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Q8_0/MAI-DS-R1-Q8_0-00015-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Q8_0/MAI-DS-R1-Q8_0-00007-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Q8_0/MAI-DS-R1-Q8_0-00011-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Q8_0/MAI-DS-R1-Q8_0-00002-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Q8_0/MAI-DS-R1-Q8_0-00008-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Q8_0/MAI-DS-R1-Q8_0-00006-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Q8_0/MAI-DS-R1-Q8_0-00014-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Q8_0/MAI-DS-R1-Q8_0-00012-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Q8_0/MAI-DS-R1-Q8_0-00009-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Q8_0/MAI-DS-R1-Q8_0-00010-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Q8_0/MAI-DS-R1-Q8_0-00013-of-00015.gguf filter=lfs diff=lfs merge=lfs -text
Q8_0/MAI-DS-R1-Q8_0-00001-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329a0bf2322201d832f6de7a2c9d5b3c0098f1d847c8ad7fad92ad596999da74
3
+ size 47784555904
Q8_0/MAI-DS-R1-Q8_0-00002-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11a557cb405231a16502f5820fb85296d76c87fa4b0b4f654f6b27376ea9581b
3
+ size 48927728256
Q8_0/MAI-DS-R1-Q8_0-00003-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f179e727e9aa2c67d716c032bc7d116ccbb8e2bdc899c35f0fdff5a633c5f71
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00004-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a38237ad8c6f76c19a25b9698781fd20675bfc82355e47345b60132e851cb17
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00005-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea832983975babdd0367618a4c4ed98d3e4d5682c52ecddd0889d37c38eeb00
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00006-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea410f0c814cb3cf7f78289159dcca60f3a89459e304cdb226c0c4a959b73960
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00007-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3e37494dc4fdeec933d9934b92da45734b49252fd9ae688824a401cfdd931e0
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00008-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e8fa5ca4a1ad2cd198ff3bace11e0b8c84a03c1c0d77dbd2de5aebd265c7f7
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00009-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7572a2516b990045383a7e0fbd89b8fdea7b677ba7f6f3dc2d285b177e9db7e1
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00010-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0ea16c8f80fda6ecd7c8cfd45a6df56aba2fa2ac3fd85e9566d7bf85ab54f3d
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00011-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7326184111f50a565d84f565b8b70bbef7e0ef581951840238ebe907027c53d
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00012-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26bd7f4419e97b53fb9a42fc53b3b2499b75f84e488cfd0f7bffb932bd51d25d
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00013-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e2e1beb4ce8ee3b1cb88f4dc41bce7cedb38714198c9ffc8eed40d05bf46ec
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00014-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bb482f4884ef8693f176eac568b106f6094a986da26de24f241f048f48d3b50
3
+ size 48927728320
Q8_0/MAI-DS-R1-Q8_0-00015-of-00015.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5ca8361f4ad833dd8b192447e4829a177b46e9a291eba1e2b14cd3d50dafb7
3
+ size 29441495680
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pretraining_tp": 1,
36
+ "q_lora_rank": 1536,
37
+ "qk_nope_head_dim": 128,
38
+ "qk_rope_head_dim": 64,
39
+ "rms_norm_eps": 1e-06,
40
+ "rope_scaling": {
41
+ "beta_fast": 32,
42
+ "beta_slow": 1,
43
+ "factor": 40,
44
+ "mscale": 1.0,
45
+ "mscale_all_dim": 1.0,
46
+ "original_max_position_embeddings": 4096,
47
+ "type": "yarn"
48
+ },
49
+ "rope_theta": 10000,
50
+ "routed_scaling_factor": 2.5,
51
+ "scoring_func": "sigmoid",
52
+ "seq_aux": true,
53
+ "tie_word_embeddings": false,
54
+ "topk_group": 4,
55
+ "topk_method": "noaux_tc",
56
+ "torch_dtype": "bfloat16",
57
+ "transformers_version": "4.46.3",
58
+ "use_cache": true,
59
+ "v_head_dim": 128,
60
+ "vocab_size": 129280
61
+ }