justheuristic
commited on
Commit
•
8a8b4d9
1
Parent(s):
21b135a
1bit test
Browse files- config.json +3 -3
- generation_config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -18,7 +18,7 @@
|
|
18 |
"num_key_value_heads": 32,
|
19 |
"pretraining_tp": 1,
|
20 |
"quantization_config": {
|
21 |
-
"in_group_size":
|
22 |
"linear_weights_not_to_quantize": [
|
23 |
"model.layers.0.input_layernorm.weight",
|
24 |
"model.layers.0.post_attention_layernorm.weight",
|
@@ -98,7 +98,7 @@
|
|
98 |
"rope_theta": 10000.0,
|
99 |
"tie_word_embeddings": false,
|
100 |
"torch_dtype": "float16",
|
101 |
-
"transformers_version": "4.
|
102 |
"use_cache": true,
|
103 |
"vocab_size": 32000
|
104 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "converted_llama2",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
|
|
18 |
"num_key_value_heads": 32,
|
19 |
"pretraining_tp": 1,
|
20 |
"quantization_config": {
|
21 |
+
"in_group_size": 16,
|
22 |
"linear_weights_not_to_quantize": [
|
23 |
"model.layers.0.input_layernorm.weight",
|
24 |
"model.layers.0.post_attention_layernorm.weight",
|
|
|
98 |
"rope_theta": 10000.0,
|
99 |
"tie_word_embeddings": false,
|
100 |
"torch_dtype": "float16",
|
101 |
+
"transformers_version": "4.40.1",
|
102 |
"use_cache": true,
|
103 |
"vocab_size": 32000
|
104 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.40.1"
|
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 sha256:82fbc31138dbee9afcb8658b27ed77b5ad9bc47a4257c4111dd35ea96e28b70c
|
3 |
+
size 1806888664
|