georgiyozhegov
commited on
Commit
•
cc6265c
1
Parent(s):
833fb7f
Upload LlamaForCausalLM
Browse files- README.md +3 -0
- config.json +7 -7
- generation_config.json +6 -0
- model.safetensors +2 -2
README.md
CHANGED
@@ -4,6 +4,9 @@ datasets:
|
|
4 |
library_name: transformers
|
5 |
license: mit
|
6 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
7 |
---
|
8 |
|
9 |
Model-calculator.
|
|
|
4 |
library_name: transformers
|
5 |
license: mit
|
6 |
pipeline_tag: text-generation
|
7 |
+
tags:
|
8 |
+
- trl
|
9 |
+
- sft
|
10 |
---
|
11 |
|
12 |
Model-calculator.
|
config.json
CHANGED
@@ -1,21 +1,21 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "model",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_bias": false,
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 1,
|
9 |
"eos_token_id": 2,
|
|
|
10 |
"hidden_act": "silu",
|
11 |
-
"hidden_size":
|
12 |
"initializer_range": 0.02,
|
13 |
-
"intermediate_size":
|
14 |
"max_position_embeddings": 256,
|
15 |
"mlp_bias": false,
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 8,
|
18 |
-
"num_hidden_layers":
|
19 |
"num_key_value_heads": 8,
|
20 |
"pretraining_tp": 1,
|
21 |
"rms_norm_eps": 1e-06,
|
@@ -23,7 +23,7 @@
|
|
23 |
"rope_theta": 10000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float32",
|
26 |
-
"transformers_version": "4.
|
27 |
"use_cache": true,
|
28 |
-
"vocab_size":
|
29 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
],
|
5 |
"attention_bias": false,
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
"eos_token_id": 2,
|
9 |
+
"head_dim": 32,
|
10 |
"hidden_act": "silu",
|
11 |
+
"hidden_size": 256,
|
12 |
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 1024,
|
14 |
"max_position_embeddings": 256,
|
15 |
"mlp_bias": false,
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 8,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
"num_key_value_heads": 8,
|
20 |
"pretraining_tp": 1,
|
21 |
"rms_norm_eps": 1e-06,
|
|
|
23 |
"rope_theta": 10000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.46.1",
|
27 |
"use_cache": true,
|
28 |
+
"vocab_size": 128
|
29 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.46.1"
|
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 sha256:51e9b97561a8e2fbb11dc583cfa26f9932d460ef1f836ae66c6da805db0e9afa
|
3 |
+
size 25447424
|