peterschmidt85
commited on
Commit
•
b3ba51e
1
Parent(s):
4520ac8
Upload LlamaForCausalLM
Browse files- config.json +6 -6
- generation_config.json +2 -1
- pytorch_model.bin +3 -0
config.json
CHANGED
@@ -1,19 +1,19 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "NousResearch/Llama-2-
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
9 |
-
"hidden_size":
|
10 |
"initializer_range": 0.02,
|
11 |
-
"intermediate_size":
|
12 |
"max_position_embeddings": 4096,
|
13 |
"model_type": "llama",
|
14 |
-
"num_attention_heads":
|
15 |
-
"num_hidden_layers":
|
16 |
-
"num_key_value_heads":
|
17 |
"pad_token_id": 0,
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-05,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"bos_token_id": 1,
|
7 |
"eos_token_id": 2,
|
8 |
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
"max_position_embeddings": 4096,
|
13 |
"model_type": "llama",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"num_key_value_heads": 32,
|
17 |
"pad_token_id": 0,
|
18 |
"pretraining_tp": 1,
|
19 |
"rms_norm_eps": 1e-05,
|
generation_config.json
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
|
|
4 |
"eos_token_id": 2,
|
5 |
-
"pad_token_id":
|
6 |
"temperature": 0.9,
|
7 |
"top_p": 0.6,
|
8 |
"transformers_version": "4.31.0"
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
+
"do_sample": true,
|
5 |
"eos_token_id": 2,
|
6 |
+
"pad_token_id": 32000,
|
7 |
"temperature": 0.9,
|
8 |
"top_p": 0.6,
|
9 |
"transformers_version": "4.31.0"
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aae23aeb74f2878766d5c1e272543e147214ab1cd6fa1c2a2b59b6af940f817
|
3 |
+
size 262188945
|