Hugging Face's logo

ludis
/
tsukasa-limarp-7b-gguf

Transformers
GGUF
llama
Inference Endpoints
text-generation-inference
Model card Files Community
ludis commited on
Commit
470c618
•
1 Parent(s): 94d0a95

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. .gitattributes +12 -0
  2. README.md +3 -4
  3. config.json +3 -0
  4. huggingface-metadata.txt +4 -0
  5. tsukasa-limarp-7b-Q2_K.gguf +3 -0
  6. tsukasa-limarp-7b-Q3_K_L.gguf +3 -0
  7. tsukasa-limarp-7b-Q3_K_M.gguf +3 -0
  8. tsukasa-limarp-7b-Q3_K_S.gguf +3 -0
  9. tsukasa-limarp-7b-Q4_K_M.gguf +3 -0
  10. tsukasa-limarp-7b-Q4_K_S.gguf +3 -0
  11. tsukasa-limarp-7b-Q5_K_M.gguf +3 -0
  12. tsukasa-limarp-7b-Q5_K_S.gguf +3 -0
  13. tsukasa-limarp-7b-Q6_K.gguf +3 -0
  14. tsukasa-limarp-7b-Q8_0.gguf +3 -0
  15. tsukasa-limarp-7b-f16.gguf +3 -0
  16. tsukasa-limarp-7b-f32.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,15 @@ 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
+ tsukasa-limarp-7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ tsukasa-limarp-7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ tsukasa-limarp-7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ tsukasa-limarp-7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ tsukasa-limarp-7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
41
+ tsukasa-limarp-7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
42
+ tsukasa-limarp-7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ tsukasa-limarp-7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ tsukasa-limarp-7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
45
+ tsukasa-limarp-7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
46
+ tsukasa-limarp-7b-f16.gguf filter=lfs diff=lfs merge=lfs -text
47
+ tsukasa-limarp-7b-f32.gguf filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -7,7 +7,6 @@ datasets:
7
  ## Base Model
8
 
9
  native fine tune of ludis/tsukasa-7b
10
- gguf converted/quantized version of ludis/tsukasa-limarp-7b
11
 
12
  ## Prompting
13
 
@@ -17,10 +16,10 @@ The `<|system|>` prompt can be used to inject out-of-channel information behind
17
 
18
  ## Benchmarks
19
 
20
- trained on commit de693ac of the koishi dataset for 1 epoch as apart of ludis/tsukasa-7b
21
 
22
- trained on commit 36fc235 of pippa metharme for 1 epoch as apart of ludis/tsukasa-7b
23
 
24
- trained on Version 2023-09-03 of LimaRP (without ponyville, lolicit, all the fallen, and eka's portal subsets) for 2 epochs
25
 
26
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f38f3a89203d118da8b477/lvXgfxrb5v4ceEtZfVrYP.png)
 
7
  ## Base Model
8
 
9
  native fine tune of ludis/tsukasa-7b
 
10
 
11
  ## Prompting
12
 
 
16
 
17
  ## Benchmarks
18
 
19
+ trained on commit de693ac of the koishi dataset
20
 
21
+ trained on commit 36fc235 of pippa metharme
22
 
23
+ trained on Version 2023-09-03 of LimaRP (without ponyville, lolicit, all the fallen, and eka's portal subsets)
24
 
25
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64f38f3a89203d118da8b477/lvXgfxrb5v4ceEtZfVrYP.png)
config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "model_type": "llama"
3
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ url: https://huggingface.co/ludis/tsukasa-limarp-7b-ggml
2
+ branch: main
3
+ download date: 2023-09-03 23:09:54
4
+
tsukasa-limarp-7b-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cbb485e7bef0cf752fff37300ece212d66d494f1cab03a0fb959b56d55469d7
3
+ size 2825954880
tsukasa-limarp-7b-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ab409ef87fde6536520b7bd74bae36a15c9b1b1d3eeb6e789e983b2d47024f0
3
+ size 3597126432
tsukasa-limarp-7b-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73e53c511b29d2cfdf62930477f3d4021636aac65432f755438c63fb42a1a295
3
+ size 3298020128
tsukasa-limarp-7b-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:249113371f4f5c234b53608787fd96fc0735244d6418a2af03d68628516eedea
3
+ size 2948320032
tsukasa-limarp-7b-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32e4c96fa46d64c2a1c2c8f74104b8d53c4e39f122d7d9553f0f54399b6b0511
3
+ size 4081021312
tsukasa-limarp-7b-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cc676bc275eb555bf137a54290d9b3ffefdfea444adba053d4d4dd0a9df8d29
3
+ size 3856757120
tsukasa-limarp-7b-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f8c7e6c007f2fc109e4a756e21e3b60a68ec4ad4caa1eb354f2a2372db7d572
3
+ size 4783175552
tsukasa-limarp-7b-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3a0e9942e36ca872b0c07487ca06a8ff8caf8f004f04a3dc39e52789da53da7
3
+ size 4651710336
tsukasa-limarp-7b-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d124417df47f569af5879e5422ba688e596ee3c8b9283641b8e83fa93274be
3
+ size 5529214432
tsukasa-limarp-7b-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23626e4f9c51f648e62c008406b88e629e54959eb97dc8053776489fe617db33
3
+ size 7161115904
tsukasa-limarp-7b-f16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1af7f085c1baa2895638940bdf5d6c2c5e46485c5983d1e7781795fa108bfc32
3
+ size 13478153984
tsukasa-limarp-7b-f32.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebf7ecd6e1c89201576954f4ab678c00363e8ce8ebe24db6495f6b37e44090dd
3
+ size 26954501856