LoneStriker commited on
Commit
9d5ef61
1 Parent(s): 663e504

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca4a474f91a58f66d98eada50af48c715138281b47702012ab487d2dcbc4a5d
3
+ size 17309173632
Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c7225885266a271d812a36cac6d0e49aef3a749ea7c0af209c69014e30a801f
3
+ size 24167589760
Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f60f83fef0331f687ae96ddf2ca236076a88cbedd538a24bd6fc963548f7bc6
3
+ size 22544394112
Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a3111e71569db4b69c67a1102272eb5440f774ce459215ff38ec3b0252c4b6
3
+ size 20430464896
Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953a5de56d3bcfe55d42db6685a63048570aec32c8dd5525c3b3c0747163b646
3
+ size 28446410624
Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a81c311a65a720b848d28df1906212f5c6102a2b4c6523dd83e83512051b93e9
3
+ size 26743523200
Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a53ba1a31bd2f92006247844056d854521df0664320b9810fd548d07491fd49
3
+ size 33227523968
Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f4e9eb6f1689f3f23e5ae6cc92361914b802b5c4115a480a82fd06478c8f859
3
+ size 32229279616
Air-Striker-Mixtral-8x7B-Instruct-ZLoss-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3338d30dc991ac026f0d10d45a1e89662b6e278dfb3ae79c0acb962d31e041b6
3
+ size 38378760064
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ pipeline_tag: text-generation
7
+ tags:
8
+ - mixtral
9
+ - mergekit
10
+ - merge
11
+ license: apache-2.0
12
+ datasets:
13
+ - jondurbin/airoboros-3.2
14
+ ---
15
+
16
+ # Air-Striker-Mixtral-8x7B-Instruct-ZLoss
17
+
18
+ Experimental model, trained using config and [Transformers/Axolotl](https://github.com/DocShotgun/axolotl) forks provided by [Doctor-Shotgun](https://huggingface.co/Doctor-Shotgun)
19
+
20
+ Model was fine-tuned from [Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) with airoboros-3.2 dataset, for 4 epochs, ChatML prompt format at 8K context length.
21
+
22
+ Additionally, model was then merged with [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1):
23
+
24
+ ---
25
+
26
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
27
+
28
+ ## Merge Details
29
+ ### Merge Method
30
+
31
+ This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
32
+
33
+ ### Models Merged
34
+
35
+ The following models were included in the merge:
36
+ * mistralai/Mixtral-8x7B-Instruct-v0.1
37
+ * LoneStriker/Air-Striker-Mixtral-8x7B-ZLoss
38
+
39
+ ### Configuration
40
+
41
+ The following YAML configuration was used to produce this model:
42
+
43
+ ```yaml
44
+ models:
45
+ - model: mistralai/Mixtral-8x7B-Instruct-v0.1
46
+ parameters:
47
+ weight: 0.5
48
+ - model: LoneStriker/Air-Striker-Mixtral-8x7B-ZLoss
49
+ parameters:
50
+ weight: 0.5
51
+ merge_method: linear
52
+ dtype: bfloat16
53
+ ```
mergekit_config.yml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: mistralai/Mixtral-8x7B-Instruct-v0.1
3
+ parameters:
4
+ weight: 0.5
5
+ - model: LoneStriker/Air-Striker-Mixtral-8x7B-ZLoss
6
+ parameters:
7
+ weight: 0.5
8
+ merge_method: linear
9
+ dtype: bfloat16
10
+