Push model using huggingface_hub.
Browse files- config.json +8 -25
- model.safetensors +1 -1
config.json
CHANGED
@@ -1,26 +1,9 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
|
10 |
-
"intermediate_size": 14336,
|
11 |
-
"max_position_embeddings": 32768,
|
12 |
-
"model_type": "llama",
|
13 |
-
"num_attention_heads": 32,
|
14 |
-
"num_hidden_layers": 1,
|
15 |
-
"num_key_value_heads": 8,
|
16 |
-
"pretraining_tp": 1,
|
17 |
-
"rms_norm_eps": 1e-05,
|
18 |
-
"rope_scaling": null,
|
19 |
-
"rope_theta": 10000.0,
|
20 |
-
"sliding_window": 4096,
|
21 |
-
"tie_word_embeddings": false,
|
22 |
-
"torch_dtype": "float16",
|
23 |
-
"transformers_version": "4.40.1",
|
24 |
-
"use_cache": true,
|
25 |
-
"vocab_size": 32000
|
26 |
-
}
|
|
|
1 |
{
|
2 |
+
"bias": true,
|
3 |
+
"depth": 5,
|
4 |
+
"load_emb": false,
|
5 |
+
"path": null,
|
6 |
+
"threshold": 1,
|
7 |
+
"top_k": 8,
|
8 |
+
"total_tokens": 63
|
9 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1530955232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72542d7eaa3278a18df0d63e1aeeb85c078f5aff23c68abc9ad1e83ffbdc31b0
|
3 |
size 1530955232
|