Add MTP
Browse files- config.json +4 -3
- generation_config.json +4 -4
- hf_quant_config.json +3 -2
- model-00001-of-00010.safetensors β model-00001-of-00011.safetensors +1 -1
- model-00002-of-00010.safetensors β model-00002-of-00011.safetensors +1 -1
- model-00003-of-00010.safetensors β model-00003-of-00011.safetensors +1 -1
- model-00004-of-00010.safetensors β model-00004-of-00011.safetensors +1 -1
- model-00005-of-00010.safetensors β model-00005-of-00011.safetensors +1 -1
- model-00006-of-00010.safetensors β model-00006-of-00011.safetensors +1 -1
- model-00007-of-00010.safetensors β model-00007-of-00011.safetensors +1 -1
- model-00008-of-00010.safetensors β model-00008-of-00011.safetensors +1 -1
- model-00009-of-00010.safetensors β model-00009-of-00011.safetensors +1 -1
- model-00010-of-00010.safetensors +0 -3
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +2 -2
config.json
CHANGED
|
@@ -87,7 +87,7 @@
|
|
| 87 |
"router_aux_loss_coef": 0.001,
|
| 88 |
"shared_expert_intermediate_size": 512,
|
| 89 |
"tie_word_embeddings": false,
|
| 90 |
-
"transformers_version": "4.57.
|
| 91 |
"use_cache": true,
|
| 92 |
"use_sliding_window": false,
|
| 93 |
"vocab_size": 151936,
|
|
@@ -352,7 +352,8 @@
|
|
| 352 |
"model.layers.9.linear_attn.in_proj_ba",
|
| 353 |
"model.layers.9.linear_attn.in_proj_qkvz",
|
| 354 |
"model.layers.9.mlp.gate",
|
| 355 |
-
"model.layers.9.mlp.shared_expert_gate"
|
|
|
|
| 356 |
],
|
| 357 |
"quant_algo": "NVFP4",
|
| 358 |
"kv_cache_scheme": {
|
|
@@ -362,7 +363,7 @@
|
|
| 362 |
},
|
| 363 |
"producer": {
|
| 364 |
"name": "modelopt",
|
| 365 |
-
"version": "0.0.1.
|
| 366 |
},
|
| 367 |
"quant_method": "modelopt"
|
| 368 |
}
|
|
|
|
| 87 |
"router_aux_loss_coef": 0.001,
|
| 88 |
"shared_expert_intermediate_size": 512,
|
| 89 |
"tie_word_embeddings": false,
|
| 90 |
+
"transformers_version": "4.57.1",
|
| 91 |
"use_cache": true,
|
| 92 |
"use_sliding_window": false,
|
| 93 |
"vocab_size": 151936,
|
|
|
|
| 352 |
"model.layers.9.linear_attn.in_proj_ba",
|
| 353 |
"model.layers.9.linear_attn.in_proj_qkvz",
|
| 354 |
"model.layers.9.mlp.gate",
|
| 355 |
+
"model.layers.9.mlp.shared_expert_gate",
|
| 356 |
+
"mtp.layers.0*"
|
| 357 |
],
|
| 358 |
"quant_algo": "NVFP4",
|
| 359 |
"kv_cache_scheme": {
|
|
|
|
| 363 |
},
|
| 364 |
"producer": {
|
| 365 |
"name": "modelopt",
|
| 366 |
+
"version": "0.0.1.dev443+gc9e06886e.d20260206"
|
| 367 |
},
|
| 368 |
"quant_method": "modelopt"
|
| 369 |
}
|
generation_config.json
CHANGED
|
@@ -2,12 +2,12 @@
|
|
| 2 |
"bos_token_id": 151643,
|
| 3 |
"do_sample": true,
|
| 4 |
"eos_token_id": [
|
| 5 |
-
|
| 6 |
-
|
| 7 |
],
|
| 8 |
"pad_token_id": 151643,
|
| 9 |
"temperature": 0.7,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.8,
|
| 12 |
-
"transformers_version": "4.57.
|
| 13 |
-
}
|
|
|
|
| 2 |
"bos_token_id": 151643,
|
| 3 |
"do_sample": true,
|
| 4 |
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
],
|
| 8 |
"pad_token_id": 151643,
|
| 9 |
"temperature": 0.7,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.0.dev0"
|
| 13 |
+
}
|
hf_quant_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"producer": {
|
| 3 |
"name": "modelopt",
|
| 4 |
-
"version": "0.0.1.
|
| 5 |
},
|
| 6 |
"quantization": {
|
| 7 |
"quant_algo": "NVFP4",
|
|
@@ -248,7 +248,8 @@
|
|
| 248 |
"model.layers.9.linear_attn.in_proj_ba",
|
| 249 |
"model.layers.9.linear_attn.in_proj_qkvz",
|
| 250 |
"model.layers.9.mlp.gate",
|
| 251 |
-
"model.layers.9.mlp.shared_expert_gate"
|
|
|
|
| 252 |
]
|
| 253 |
}
|
| 254 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"producer": {
|
| 3 |
"name": "modelopt",
|
| 4 |
+
"version": "0.0.1.dev443+gc9e06886e.d20260206"
|
| 5 |
},
|
| 6 |
"quantization": {
|
| 7 |
"quant_algo": "NVFP4",
|
|
|
|
| 248 |
"model.layers.9.linear_attn.in_proj_ba",
|
| 249 |
"model.layers.9.linear_attn.in_proj_qkvz",
|
| 250 |
"model.layers.9.mlp.gate",
|
| 251 |
+
"model.layers.9.mlp.shared_expert_gate",
|
| 252 |
+
"mtp.layers.0*"
|
| 253 |
]
|
| 254 |
}
|
| 255 |
}
|
model-00001-of-00010.safetensors β model-00001-of-00011.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5003036968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2432c420ab12ae5109e63bec3a12076c9651bf717245a59ceee00d299725a08b
|
| 3 |
size 5003036968
|
model-00002-of-00010.safetensors β model-00002-of-00011.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5003483960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0be1603d7a3512b643e0af4632b2cc5e568a8cc07c618d779646e91a42a60086
|
| 3 |
size 5003483960
|
model-00003-of-00010.safetensors β model-00003-of-00011.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5003514400
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f38337b058eb06d6290a5d3c407b452921bfc351c25293882f77fabe6936f4c9
|
| 3 |
size 5003514400
|
model-00004-of-00010.safetensors β model-00004-of-00011.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5003755712
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ad60f38a2fbfe2aea0bae6d6efafa80bc496984d832430a08503a0349c824e3
|
| 3 |
size 5003755712
|
model-00005-of-00010.safetensors β model-00005-of-00011.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5003581304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91683c98c4594079005cb2eaf35f45945f1a1a22a12daba8962203665893436f
|
| 3 |
size 5003581304
|
model-00006-of-00010.safetensors β model-00006-of-00011.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5003516056
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c19190847278b7ba2bafe1928bf7566162bcb1534825accb98116bc7ddfff8fd
|
| 3 |
size 5003516056
|
model-00007-of-00010.safetensors β model-00007-of-00011.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5003593008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35c51ab71581678a014b0c9350495439ac7b662d90b7fe02fee8ed1c05cfb7a8
|
| 3 |
size 5003593008
|
model-00008-of-00010.safetensors β model-00008-of-00011.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5003516072
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c20ca2472189edba57b2e7ee410da91782f293654f29fa82cce6390d3e05591e
|
| 3 |
size 5003516072
|
model-00009-of-00010.safetensors β model-00009-of-00011.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5003744824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59c7b3a6c88d7a1e6979858dcee4e40dbdf0e005bb8b284d62beaa70efc84f22
|
| 3 |
size 5003744824
|
model-00010-of-00010.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1ec3f7e8aa5cd222cfc0e0f44c51152cfad491312c4f1b073e1928693c6eebb3
|
| 3 |
-
size 2424868248
|
|
|
|
|
|
|
|
|
|
|
|
model-00010-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12d5a6161676e0c3b7f398edb9424d3476391933a73cb44401bdcd3d12ff3eea
|
| 3 |
+
size 5000330496
|
model-00011-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57215c4d31f794dd3868e62941492d33df28054feb38dee1a1f32d65481216e1
|
| 3 |
+
size 725675520
|
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:f9c2f67f083110def2b0d727e2b90b9eeb5179b7cc400a450880da4d04abb47d
|
| 3 |
+
size 28463294
|