Upload LlamaForCausalLM
#4
by
WesleySantos
- opened
- config.json +2 -3
- pytorch_model-00001-of-00002.bin +1 -1
- pytorch_model-00002-of-00002.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -9,7 +9,7 @@
|
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 11008,
|
12 |
-
"max_position_embeddings":
|
13 |
"model_type": "llama",
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
@@ -18,7 +18,6 @@
|
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_scaling": null,
|
21 |
-
"rope_theta": 10000.0,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.31.0",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "daryl149/llama-2-7b-chat-hf",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
9 |
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
"model_type": "llama",
|
14 |
"num_attention_heads": 32,
|
15 |
"num_hidden_layers": 32,
|
|
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-06,
|
20 |
"rope_scaling": null,
|
|
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
"transformers_version": "4.31.0",
|
pytorch_model-00001-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9976634558
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5b9108916566f9bfbbc5832c04ff140fe0873cbc596b49c001fb7a624aff383
|
3 |
size 9976634558
|
pytorch_model-00002-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3500315539
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:626b1ae30cb7806b5b9f6c087adaa7c5addb4774db539ed610ec7e55aece486b
|
3 |
size 3500315539
|