Upload Gemma2ForCausalLM
Browse files- config.json +2 -31
- generation_config.json +1 -5
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -6,44 +6,15 @@
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"attn_logit_softcapping": 50.0,
|
| 8 |
"bos_token_id": 2,
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"eos_token_id": [
|
| 12 |
-
1,
|
| 13 |
-
107
|
| 14 |
-
],
|
| 15 |
"final_logit_softcapping": 30.0,
|
| 16 |
"head_dim": 256,
|
| 17 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 18 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 19 |
"hidden_size": 8,
|
| 20 |
"initializer_range": 0.02,
|
| 21 |
"intermediate_size": 32,
|
| 22 |
"layer_types": [
|
| 23 |
-
"sliding_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"sliding_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"sliding_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"sliding_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"sliding_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"sliding_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"sliding_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"sliding_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"sliding_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"sliding_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"sliding_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"sliding_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
"sliding_attention",
|
| 48 |
"full_attention"
|
| 49 |
],
|
|
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"attn_logit_softcapping": 50.0,
|
| 8 |
"bos_token_id": 2,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"eos_token_id": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"final_logit_softcapping": 30.0,
|
| 12 |
"head_dim": 256,
|
|
|
|
| 13 |
"hidden_activation": "gelu_pytorch_tanh",
|
| 14 |
"hidden_size": 8,
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
"intermediate_size": 32,
|
| 17 |
"layer_types": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
"sliding_attention",
|
| 19 |
"full_attention"
|
| 20 |
],
|
generation_config.json
CHANGED
|
@@ -1,11 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 2,
|
| 4 |
-
"
|
| 5 |
-
"eos_token_id": [
|
| 6 |
-
1,
|
| 7 |
-
107
|
| 8 |
-
],
|
| 9 |
"pad_token_id": 0,
|
| 10 |
"transformers_version": "4.57.0.dev0"
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"pad_token_id": 0,
|
| 6 |
"transformers_version": "4.57.0.dev0"
|
| 7 |
}
|
model.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 sha256:9a08a43ada8cdb5bcce4223c9202610f6fe9fce66b90439aaa80bde4b29a16cd
|
| 3 |
+
size 8397584
|