Upload of AutoGPTQ quantized model
Browse files- config.json +1 -1
- gptq_model-4bit-128g.safetensors +2 -2
- tokenizer.json +1 -6
config.json
CHANGED
@@ -21,7 +21,7 @@
|
|
21 |
"rope_scaling": null,
|
22 |
"rope_theta": 10000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
-
"torch_dtype": "
|
25 |
"transformers_version": "4.34.1",
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 65024
|
|
|
21 |
"rope_scaling": null,
|
22 |
"rope_theta": 10000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
"transformers_version": "4.34.1",
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 65024
|
gptq_model-4bit-128g.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 sha256:236b4408720afb7d12a19f9b29c78019b092819aa28fa52599488c1494962300
|
3 |
+
size 4437780008
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 2048,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|