add mtp layer
#5
by linzhao-amd - opened
- .gitattributes +1 -1
- config.json +3 -2
- generation_config.json +1 -1
- model-00001-of-00009.safetensors +1 -1
- model-00002-of-00009.safetensors +1 -1
- model-00003-of-00009.safetensors +1 -1
- model-00004-of-00009.safetensors +1 -1
- model-00005-of-00009.safetensors +1 -1
- model-00006-of-00009.safetensors +1 -1
- model-00007-of-00009.safetensors +1 -1
- model-00008-of-00009.safetensors +1 -1
- model-00009-of-00009.safetensors +2 -2
- model.safetensors.index.json +2 -2
.gitattributes
CHANGED
|
@@ -33,5 +33,5 @@ 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
|
| 36 |
-
model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
tokenizer.json 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 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
|
config.json
CHANGED
|
@@ -13,6 +13,7 @@
|
|
| 13 |
],
|
| 14 |
"ep_size": 1,
|
| 15 |
"first_k_dense_replace": 3,
|
|
|
|
| 16 |
"hidden_act": "silu",
|
| 17 |
"hidden_size": 6144,
|
| 18 |
"index_head_dim": 128,
|
|
@@ -854,7 +855,7 @@
|
|
| 854 |
"quant_method": "quark",
|
| 855 |
"quant_mode": "eager_mode",
|
| 856 |
"softmax_quant_spec": null,
|
| 857 |
-
"version": "0.
|
| 858 |
},
|
| 859 |
"rms_norm_eps": 1e-05,
|
| 860 |
"rope_interleave": true,
|
|
@@ -867,7 +868,7 @@
|
|
| 867 |
"tie_word_embeddings": false,
|
| 868 |
"topk_group": 1,
|
| 869 |
"topk_method": "noaux_tc",
|
| 870 |
-
"transformers_version": "5.
|
| 871 |
"use_cache": true,
|
| 872 |
"v_head_dim": 256,
|
| 873 |
"vocab_size": 154880
|
|
|
|
| 13 |
],
|
| 14 |
"ep_size": 1,
|
| 15 |
"first_k_dense_replace": 3,
|
| 16 |
+
"head_dim": 64,
|
| 17 |
"hidden_act": "silu",
|
| 18 |
"hidden_size": 6144,
|
| 19 |
"index_head_dim": 128,
|
|
|
|
| 855 |
"quant_method": "quark",
|
| 856 |
"quant_mode": "eager_mode",
|
| 857 |
"softmax_quant_spec": null,
|
| 858 |
+
"version": "0.13+488baccced9"
|
| 859 |
},
|
| 860 |
"rms_norm_eps": 1e-05,
|
| 861 |
"rope_interleave": true,
|
|
|
|
| 868 |
"tie_word_embeddings": false,
|
| 869 |
"topk_group": 1,
|
| 870 |
"topk_method": "noaux_tc",
|
| 871 |
+
"transformers_version": "5.2.0",
|
| 872 |
"use_cache": true,
|
| 873 |
"v_head_dim": 256,
|
| 874 |
"vocab_size": 154880
|
generation_config.json
CHANGED
|
@@ -9,5 +9,5 @@
|
|
| 9 |
"pad_token_id": 154820,
|
| 10 |
"temperature": 1.0,
|
| 11 |
"top_p": 0.95,
|
| 12 |
-
"transformers_version": "5.
|
| 13 |
}
|
|
|
|
| 9 |
"pad_token_id": 154820,
|
| 10 |
"temperature": 1.0,
|
| 11 |
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "5.2.0"
|
| 13 |
}
|
model-00001-of-00009.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 49999051524
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d056160e3a2d43d308a2083d9ec18ac40e8bf39bd4cc2d692009b4e5cf749b68
|
| 3 |
size 49999051524
|
model-00002-of-00009.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 49998227584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1ac481d97576b9b12ffa708bc2debd34e82245980826e0de77ada48d6cf40df
|
| 3 |
size 49998227584
|
model-00003-of-00009.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50000184968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0faf16ca5fb77ebb86d54c7ede11b1278621aa594a3225ad0bd5daea7f319d80
|
| 3 |
size 50000184968
|
model-00004-of-00009.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 49998227296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fb3bdacd0b7dbd3226d09d696f46f1200c8e025b37f91d03ed88a67063718df
|
| 3 |
size 49998227296
|
model-00005-of-00009.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 49916961116
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:263454897962bb1d539595be86526636df7cccf64d2010da853ade746b615b35
|
| 3 |
size 49916961116
|
model-00006-of-00009.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50002802316
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14b70f238a1313bfd607fad830c7fe5d6148d00a547be223d8262856d10c4923
|
| 3 |
size 50002802316
|
model-00007-of-00009.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 49999014384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2db7e723a8a2eafd213141eb90cfff7189c3d84b9ad8c25248b31e5e51efe80
|
| 3 |
size 49999014384
|
model-00008-of-00009.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50000185032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ba72559cf58cb0e6bd04af6d4aafcc10487999f42a3e388853f6740c0e6ae4a
|
| 3 |
size 50000185032
|
model-00009-of-00009.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd05cefd4fa774ff4c09a15ae45ec61d5b1b1c2e7032bdcc733f0fd4ae11de75
|
| 3 |
+
size 61907566876
|
model.safetensors.index.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f23d65b82e78a3c64d765704f0f473a4792760186fbb191ea8bec8c05c65ee3
|
| 3 |
+
size 22403819
|