Add abliterated DrMedra4b model
Browse files- config.json +36 -0
- generation_config.json +3 -3
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
config.json
CHANGED
@@ -20,6 +20,42 @@
|
|
20 |
"hidden_size": 2560,
|
21 |
"initializer_range": 0.02,
|
22 |
"intermediate_size": 10240,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"max_position_embeddings": 131072,
|
24 |
"model_type": "gemma3_text",
|
25 |
"num_attention_heads": 8,
|
|
|
20 |
"hidden_size": 2560,
|
21 |
"initializer_range": 0.02,
|
22 |
"intermediate_size": 10240,
|
23 |
+
"layer_types": [
|
24 |
+
"sliding_attention",
|
25 |
+
"sliding_attention",
|
26 |
+
"sliding_attention",
|
27 |
+
"sliding_attention",
|
28 |
+
"sliding_attention",
|
29 |
+
"full_attention",
|
30 |
+
"sliding_attention",
|
31 |
+
"sliding_attention",
|
32 |
+
"sliding_attention",
|
33 |
+
"sliding_attention",
|
34 |
+
"sliding_attention",
|
35 |
+
"full_attention",
|
36 |
+
"sliding_attention",
|
37 |
+
"sliding_attention",
|
38 |
+
"sliding_attention",
|
39 |
+
"sliding_attention",
|
40 |
+
"sliding_attention",
|
41 |
+
"full_attention",
|
42 |
+
"sliding_attention",
|
43 |
+
"sliding_attention",
|
44 |
+
"sliding_attention",
|
45 |
+
"sliding_attention",
|
46 |
+
"sliding_attention",
|
47 |
+
"full_attention",
|
48 |
+
"sliding_attention",
|
49 |
+
"sliding_attention",
|
50 |
+
"sliding_attention",
|
51 |
+
"sliding_attention",
|
52 |
+
"sliding_attention",
|
53 |
+
"full_attention",
|
54 |
+
"sliding_attention",
|
55 |
+
"sliding_attention",
|
56 |
+
"sliding_attention",
|
57 |
+
"sliding_attention"
|
58 |
+
],
|
59 |
"max_position_embeddings": 131072,
|
60 |
"model_type": "gemma3_text",
|
61 |
"num_attention_heads": 8,
|
generation_config.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
-
"
|
|
|
3 |
"do_sample": true,
|
4 |
"eos_token_id": [
|
5 |
1,
|
6 |
106
|
7 |
],
|
8 |
-
"
|
9 |
-
"top_p": 0.95,
|
10 |
"transformers_version": "4.52.4"
|
11 |
}
|
|
|
1 |
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
"do_sample": true,
|
5 |
"eos_token_id": [
|
6 |
1,
|
7 |
106
|
8 |
],
|
9 |
+
"pad_token_id": 0,
|
|
|
10 |
"transformers_version": "4.52.4"
|
11 |
}
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4961251752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9b185b9fcb9f7fe6a20823d000812eaf11ec5f08378b17db36b5b0ac674362e
|
3 |
size 4961251752
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4981531360
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fed8c28648261c6788d1ac3eb65bd35e985541968b1ce30fd1aeb19437633967
|
3 |
size 4981531360
|