Upload folder using huggingface_hub
Browse files- .ipynb_checkpoints/config-checkpoint.json +16 -0
- config.json +16 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +0 -0
.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"d_model": 1536,
|
3 |
+
"d_intermediate": 0,
|
4 |
+
"n_layer": 48,
|
5 |
+
"vocab_size": 50277,
|
6 |
+
"ssm_cfg": {
|
7 |
+
"layer": "Mamba2"
|
8 |
+
},
|
9 |
+
"attn_layer_idx": [],
|
10 |
+
"attn_cfg": {},
|
11 |
+
"rms_norm": true,
|
12 |
+
"residual_in_fp32": false,
|
13 |
+
"fused_add_norm": true,
|
14 |
+
"pad_vocab_size_multiple": 16,
|
15 |
+
"tie_embeddings": true
|
16 |
+
}
|
config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"d_model": 1536,
|
3 |
+
"d_intermediate": 0,
|
4 |
+
"n_layer": 48,
|
5 |
+
"vocab_size": 50277,
|
6 |
+
"ssm_cfg": {
|
7 |
+
"layer": "Mamba2"
|
8 |
+
},
|
9 |
+
"attn_layer_idx": [],
|
10 |
+
"attn_cfg": {},
|
11 |
+
"rms_norm": true,
|
12 |
+
"residual_in_fp32": false,
|
13 |
+
"fused_add_norm": true,
|
14 |
+
"pad_vocab_size_multiple": 16,
|
15 |
+
"tie_embeddings": true
|
16 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d43d31b9cca54c04ac73d5f7cfe43d969de316966278b9d6bc9e882969112eab
|
3 |
+
size 3121010792
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e27fe3a466e990311352d2f31f82c84746aedac044287c17f1505c5c8acdd35f
|
3 |
+
size 1560487250
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a0c3fb1719e605d8ab5906bcb3de19fda89d294035509519136e175ed88f84b
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2a087675a984c1c97ceb3ba878178699b271dc971445463cf024921597da7e9
|
3 |
+
size 1064
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|