Add 8bit quantized model
Browse files
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
@@ -15,6 +15,12 @@
|
|
15 |
"num_attention_heads": 16,
|
16 |
"num_hidden_layers": 28,
|
17 |
"num_steps": "global_step320000",
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
"rotary_emb_base": 10000,
|
19 |
"rotary_pct": 0.25,
|
20 |
"tie_word_embeddings": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./polyglot-5.8b-koalpaca-v1.1b",
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
|
|
15 |
"num_attention_heads": 16,
|
16 |
"num_hidden_layers": 28,
|
17 |
"num_steps": "global_step320000",
|
18 |
+
"quantization_config": {
|
19 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
20 |
+
"llm_int8_skip_modules": null,
|
21 |
+
"llm_int8_threshold": 6.0,
|
22 |
+
"load_in_8bit": true
|
23 |
+
},
|
24 |
"rotary_emb_base": 10000,
|
25 |
"rotary_pct": 0.25,
|
26 |
"tie_word_embeddings": false,
|
pytorch_model-00001-of-00002.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b088704796dab521146f1309a6e6eb2e936cc255f01f2101fbf36dee9f94be45
|
3 |
-
size 10017673915
|
|
|
|
|
|
|
|
pytorch_model-00002-of-00002.bin → pytorch_model.bin
RENAMED
@@ -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 sha256:0e9e227fdfe4b23600ef74a1420248ee839de65ab25a058b7d4432859e55923c
|
3 |
+
size 6254727565
|