Upload MistralForCausalLM
Browse files
config.json
CHANGED
@@ -4,8 +4,8 @@
|
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
-
"bos_token_id":
|
8 |
-
"eos_token_id":
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 4096,
|
11 |
"initializer_range": 0.02,
|
@@ -15,12 +15,11 @@
|
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
18 |
-
"pad_token_id": 32001,
|
19 |
"rms_norm_eps": 1e-05,
|
20 |
"rope_theta": 1000000.0,
|
21 |
"sliding_window": null,
|
22 |
"tie_word_embeddings": false,
|
23 |
-
"torch_dtype": "
|
24 |
"transformers_version": "4.40.0",
|
25 |
"use_cache": true,
|
26 |
"vocab_size": 32002
|
|
|
4 |
"MistralForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 4096,
|
11 |
"initializer_range": 0.02,
|
|
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 32,
|
17 |
"num_key_value_heads": 8,
|
|
|
18 |
"rms_norm_eps": 1e-05,
|
19 |
"rope_theta": 1000000.0,
|
20 |
"sliding_window": null,
|
21 |
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float32",
|
23 |
"transformers_version": "4.40.0",
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 32002
|
model-00001-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4987229704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:328590eb5b8d613e243b7abec65a9a14f9bbe1fd3c7e9e3d03998a59dd0ce615
|
3 |
size 4987229704
|
model-00002-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4899116440
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:121cdafbf1dd5e27b013c0c8d4116b73269ede347c4c0dee838af485e6aa6368
|
3 |
size 4899116440
|
model-00003-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999813120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1451429028080db788c9bd27c05198f50e25fef14aacf84616f4361f1047fe10
|
3 |
size 4999813120
|
model-00004-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999813128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4917a70287f2b1b72d1c5c7a60202f685ae70c3e4ef9c584813638f01052ae76
|
3 |
size 4999813128
|
model-00005-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4832007496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa8d8eda44a5752a341b32dacf369eb03bbc575316e79ff6048903dbf1227933
|
3 |
size 4832007496
|
model-00006-of-00006.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4249047664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de3bdfe520dc3a1795eabb77501c3ea1a40562b5099d4a5dd62fc12b3a3a0ed8
|
3 |
size 4249047664
|