Improved quantization using Openvino 2024.5.0rc1
Browse files- README.md +4 -5
- config.json +1 -1
- generation_config.json +1 -1
- openvino_model.bin +2 -2
- openvino_model.xml +0 -0
README.md
CHANGED
@@ -7,21 +7,20 @@ tags:
|
|
7 |
|
8 |
This is an INT4 quantized version of the `mistralai/Mistral-7B-Instruct-v0.2` model. The Python packages used in creating this model are as follows:
|
9 |
```
|
10 |
-
openvino==2024.
|
11 |
optimum==1.23.3
|
12 |
optimum-intel==1.20.1
|
13 |
nncf==2.13.0
|
14 |
torch==2.5.1
|
15 |
-
transformers==4.46.
|
16 |
```
|
17 |
This quantized model is created using the following command:
|
18 |
```
|
19 |
-
optimum-cli export openvino
|
20 |
```
|
21 |
For more details, run the following command from your Python environment: `optimum-cli export openvino --help`
|
22 |
|
23 |
INFO:nncf:Statistics of the bitwidth distribution:
|
24 |
| Num bits (N) | % all parameters (layers) | % ratio-defining parameters (layers) |
|
25 |
|----------------|-----------------------------|----------------------------------------|
|
26 |
-
|
|
27 |
-
| 4 | 96% (224 / 226) | 100% (224 / 224) |
|
|
|
7 |
|
8 |
This is an INT4 quantized version of the `mistralai/Mistral-7B-Instruct-v0.2` model. The Python packages used in creating this model are as follows:
|
9 |
```
|
10 |
+
openvino==2024.5.0rc1
|
11 |
optimum==1.23.3
|
12 |
optimum-intel==1.20.1
|
13 |
nncf==2.13.0
|
14 |
torch==2.5.1
|
15 |
+
transformers==4.46.2
|
16 |
```
|
17 |
This quantized model is created using the following command:
|
18 |
```
|
19 |
+
optimum-cli export openvino --model "mistralai/Mistral-7B-Instruct-v0.2" --weight-format int4 --group-size 128 --sym --ratio 1 --all-layers ./Mistral-7B-Instruct-v0.2-ov-int4
|
20 |
```
|
21 |
For more details, run the following command from your Python environment: `optimum-cli export openvino --help`
|
22 |
|
23 |
INFO:nncf:Statistics of the bitwidth distribution:
|
24 |
| Num bits (N) | % all parameters (layers) | % ratio-defining parameters (layers) |
|
25 |
|----------------|-----------------------------|----------------------------------------|
|
26 |
+
| 4 | 100% (226 / 226) | 100% (226 / 226) |
|
|
config.json
CHANGED
@@ -22,7 +22,7 @@
|
|
22 |
"sliding_window": null,
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
-
"transformers_version": "4.46.
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 32000
|
28 |
}
|
|
|
22 |
"sliding_window": null,
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.46.2",
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 32000
|
28 |
}
|
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": "4.46.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.46.2"
|
6 |
}
|
openvino_model.bin
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 sha256:29ee4a89d73614bdcccfeca66322d6bb65bb48e924f73f2100ed7c095b6a9181
|
3 |
+
size 3734946352
|
openvino_model.xml
CHANGED
The diff for this file is too large to render.
See raw diff
|
|