Upload DeepseekV3ForCausalLM
Browse files- config.json +1 -1
- generation_config.json +0 -3
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 0,
|
| 8 |
-
"dtype": "
|
| 9 |
"eos_token_id": 1,
|
| 10 |
"first_k_dense_replace": 3,
|
| 11 |
"head_dim": 64,
|
|
|
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 0,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
"eos_token_id": 1,
|
| 10 |
"first_k_dense_replace": 3,
|
| 11 |
"head_dim": 64,
|
generation_config.json
CHANGED
|
@@ -1,9 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 0,
|
| 4 |
-
"do_sample": true,
|
| 5 |
"eos_token_id": 1,
|
| 6 |
-
"temperature": 0.6,
|
| 7 |
-
"top_p": 0.95,
|
| 8 |
"transformers_version": "4.57.3"
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 0,
|
|
|
|
| 4 |
"eos_token_id": 1,
|
|
|
|
|
|
|
| 5 |
"transformers_version": "4.57.3"
|
| 6 |
}
|
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:d811212ee31acf7be29b2188fa9d8f16bf99919e1b071474b5ab96cfe6cb7a62
|
| 3 |
+
size 11036056
|