danielhanchen
commited on
Commit
•
5933680
1
Parent(s):
b549043
Upload config
Browse files- README.md +1 -2
- config.json +5 -2
README.md
CHANGED
@@ -1,13 +1,12 @@
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
4 |
-
license: apache-2.0
|
5 |
library_name: transformers
|
|
|
6 |
tags:
|
7 |
- unsloth
|
8 |
- transformers
|
9 |
- tinyllama
|
10 |
-
|
11 |
---
|
12 |
|
13 |
|
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
|
|
4 |
library_name: transformers
|
5 |
+
license: apache-2.0
|
6 |
tags:
|
7 |
- unsloth
|
8 |
- transformers
|
9 |
- tinyllama
|
|
|
10 |
---
|
11 |
|
12 |
|
config.json
CHANGED
@@ -1,9 +1,10 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
|
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
@@ -11,6 +12,7 @@
|
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 5632,
|
13 |
"max_position_embeddings": 2048,
|
|
|
14 |
"model_type": "llama",
|
15 |
"num_attention_heads": 32,
|
16 |
"num_hidden_layers": 22,
|
@@ -22,7 +24,8 @@
|
|
22 |
"rope_theta": 10000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
-
"transformers_version": "4.
|
|
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 32000
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "unsloth/tinyllama",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 1,
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "silu",
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 5632,
|
14 |
"max_position_embeddings": 2048,
|
15 |
+
"mlp_bias": false,
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 22,
|
|
|
24 |
"rope_theta": 10000.0,
|
25 |
"tie_word_embeddings": false,
|
26 |
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.44.0",
|
28 |
+
"unsloth_version": "2024.8",
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 32000
|
31 |
}
|