OpenSourceRonin commited on
Commit
a9844c1
1 Parent(s): 531dd38

Upload model Mistral-Large-Instruct-2407-v8-k65536-256-woft

Browse files
README.md ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: other
4
+ license_name: mrl
5
+ license_link: https://mistral.ai/licenses/MRL-0.1.md
6
+ base_model:
7
+ - mistralai/Mistral-Large-Instruct-2407
8
+ base_model_relation: quantized
9
+ tags:
10
+ - VPTQ
11
+ - Quantized
12
+ - Quantization
13
+ ---
14
+ **Disclaimer**:
15
+
16
+ The model is reproduced based on the paper *VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models* [github](https://github.com/microsoft/vptq) and [arXiv](https://arxiv.org/abs/2409.17066)
17
+
18
+ The model itself is sourced from a community release.
19
+
20
+ It is intended only for experimental purposes.
21
+
22
+ Users are responsible for any consequences arising from the use of this model.
23
+
24
+ **Note**:
25
+
26
+ The PPL test results are for reference only and were collected using GPTQ testing script.
27
+
28
+ ```json
29
+ {
30
+ "ctx_2048": {
31
+ "wikitext2": 3.484158515930176,
32
+ "c4": 6.430262088775635,
33
+ "c4-new": 7.119498252868652
34
+ },
35
+ "ctx_4096": {
36
+ "wikitext2": 3.2934534549713135,
37
+ "c4": 6.052966594696045,
38
+ "c4-new": 6.734064102172852
39
+ },
40
+ "ctx_8192": {
41
+ "wikitext2": 3.1873176097869873,
42
+ "c4": 4.763023376464844,
43
+ "c4-new": 6.607855796813965
44
+ }
45
+ }
46
+ ```
config.json ADDED
The diff for this file is too large to render. See raw diff
 
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": "4.45.2"
6
+ }
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ec492f2ecb2bdb73b7b004cdf54461b63cd7c77136ba9b950841544d1af2a5c
3
+ size 4888744144
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16beba755c2fadff0d35659c50ad6fb9c8384e083b29cef9d0e08cc2b7bf5944
3
+ size 4946482296
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e056efa4b95b59394e1a3b4aa8298770c389d5007acc7e331689d80cd32b816
3
+ size 4934741544
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eea5a5b4ed74ceb9ac8167fa7323ee30678ad79503f178552f55c963ed8ce8b2
3
+ size 4877089632
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df148352684fdf95d6aedf93cb85e5a301609dfd753092dea14e36bc65456449
3
+ size 4946482392
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9e7bd002f06c687965162afad1b9e5f3ee545d4e56c91e93ba4394cfe0314b
3
+ size 4934741544
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60f7649ac3a841bb27ba1717c68da55622e3456091e921a07aef7fad3b868f3d
3
+ size 4877089632
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885a0005a2b6b99958f7d232d7cabd4c9c4ace1048de369b67b065352d6be498
3
+ size 4946482392
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f5c7d306b7112a55af6bbf639a33b22ff3ba30288bcab6518094e97278e877
3
+ size 4934741544
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76aa8676f20ff56bf57643f00a055a61229f49f4424ed06610e9a035cebf621b
3
+ size 3707313264
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
3
+ size 587583
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff