Hugging Face's logo

tmpupload
/
superhot-30b-8k-no-rlhf-test-GGML

Model card Files Community
3v324v23 commited on
Commit
fb6f09d
•
1 Parent(s): df04844

Model upload.

Browse files
Files changed (16) hide show
  1. .gitattributes +0 -2
  2. README.md +21 -0
  3. superhot-30b-8k-prototype-v2.ggmlv3.Q2_K.bin +3 -0
  4. superhot-30b-8k-prototype-v2.ggmlv3.Q3_K_L.bin +3 -0
  5. superhot-30b-8k-prototype-v2.ggmlv3.Q3_K_M.bin +3 -0
  6. superhot-30b-8k-prototype-v2.ggmlv3.Q3_K_S.bin +3 -0
  7. superhot-30b-8k-prototype-v2.ggmlv3.Q4_0.bin +3 -0
  8. superhot-30b-8k-prototype-v2.ggmlv3.Q4_1.bin +3 -0
  9. superhot-30b-8k-prototype-v2.ggmlv3.Q4_K_M.bin +3 -0
  10. superhot-30b-8k-prototype-v2.ggmlv3.Q4_K_S.bin +3 -0
  11. superhot-30b-8k-prototype-v2.ggmlv3.Q5_0.bin +3 -0
  12. superhot-30b-8k-prototype-v2.ggmlv3.Q5_1.bin +3 -0
  13. superhot-30b-8k-prototype-v2.ggmlv3.Q5_K_M.bin +3 -0
  14. superhot-30b-8k-prototype-v2.ggmlv3.Q5_K_S.bin +3 -0
  15. superhot-30b-8k-prototype-v2.ggmlv3.Q6_K.bin +3 -0
  16. superhot-30b-8k-prototype-v2.ggmlv3.Q8_0.bin +3 -0
.gitattributes CHANGED
@@ -9,7 +9,6 @@
9
  *.joblib filter=lfs diff=lfs merge=lfs -text
10
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
  *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
  *.msgpack filter=lfs diff=lfs merge=lfs -text
14
  *.npy filter=lfs diff=lfs merge=lfs -text
15
  *.npz filter=lfs diff=lfs merge=lfs -text
@@ -25,7 +24,6 @@
25
  *.safetensors filter=lfs diff=lfs merge=lfs -text
26
  saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
  *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
  *.tflite filter=lfs diff=lfs merge=lfs -text
30
  *.tgz filter=lfs diff=lfs merge=lfs -text
31
  *.wasm filter=lfs diff=lfs merge=lfs -text
 
9
  *.joblib filter=lfs diff=lfs merge=lfs -text
10
  *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
  *.mlmodel filter=lfs diff=lfs merge=lfs -text
 
12
  *.msgpack filter=lfs diff=lfs merge=lfs -text
13
  *.npy filter=lfs diff=lfs merge=lfs -text
14
  *.npz filter=lfs diff=lfs merge=lfs -text
 
24
  *.safetensors filter=lfs diff=lfs merge=lfs -text
25
  saved_model/**/* filter=lfs diff=lfs merge=lfs -text
26
  *.tar.* filter=lfs diff=lfs merge=lfs -text
 
27
  *.tflite filter=lfs diff=lfs merge=lfs -text
28
  *.tgz filter=lfs diff=lfs merge=lfs -text
29
  *.wasm filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # superhot-30b-8k-no-rlhf-test-GGML
2
+
3
+ Merged base LLaMA and LoRA with this:
4
+ https://github.com/tloen/alpaca-lora
5
+
6
+ Base LLaMA 30B:
7
+ https://huggingface.co/huggyllama/llama-30b
8
+
9
+ SuperHOT 30B 8k no-rlhf-test LoRA:
10
+ https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test
11
+
12
+ ``` sh
13
+ BASE_MODEL=huggyllama_llama-30b LORA=kaiokendev_superhot-30b-8k-no-rlhf-test python export_hf_checkpoint.py
14
+ ```
15
+
16
+ Converted and quantized with llama.cpp commit `447ccbe`:
17
+
18
+ ``` sh
19
+ python convert.py superhot-30b-8k-safetensors --outtype f32 --outfile superhot-30b-8k-no-rlhf-test.ggmlv3.f32.bin
20
+ ./bin/quantize superhot-30b-8k-no-rlhf-test.ggmlv3.f32.bin superhot-30b-8k-no-rlhf-test.ggmlv3.Q2_K.bin Q2_K
21
+ ```
superhot-30b-8k-prototype-v2.ggmlv3.Q2_K.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6bd75d4997f8a1df212cbc879b3cf44915447a8e1e6e3f4ff010c0f5b5201c5
3
+ size 13705131392
superhot-30b-8k-prototype-v2.ggmlv3.Q3_K_L.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e1465f45de97e7ef8f3512f26cf03f267828c09e42ce275a470ec54e2353b29
3
+ size 17279469952
superhot-30b-8k-prototype-v2.ggmlv3.Q3_K_M.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7151f74f0f9ef9652267b3681f72ee3ab1a3655b06100c1fc56eb3245f92d167
3
+ size 15720368512
superhot-30b-8k-prototype-v2.ggmlv3.Q3_K_S.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1b9cb2d6cdbd872e946a4aef51d6ebcd76d6a8e45fe8109c6e1171d8dc65212
3
+ size 14063823232
superhot-30b-8k-prototype-v2.ggmlv3.Q4_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa996348388640f8918477462602335e3ebe18f0d02c50c0fcaa8859edd8cac2
3
+ size 18355678592
superhot-30b-8k-prototype-v2.ggmlv3.Q4_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95b5e890dfd99cdb6db6c8665b4b2dfd2795a8cdf02f0b50336a0dc05c4975a0
3
+ size 20375375232
superhot-30b-8k-prototype-v2.ggmlv3.Q4_K_M.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d545e2abafc8c6ad896155f3ed060bdfeeca938bf02b47b9755d15f5086e0693
3
+ size 19620851072
superhot-30b-8k-prototype-v2.ggmlv3.Q4_K_S.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73de793b373c14f1182258739b40a3a79b1de19b5bfae112b21cd4c06f77eca
3
+ size 18355678592
superhot-30b-8k-prototype-v2.ggmlv3.Q5_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6f957e36464f185c44a25d8d02fd20bc1f716bf7a80c33ca8b5192042e7500
3
+ size 22395071872
superhot-30b-8k-prototype-v2.ggmlv3.Q5_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c372990cd118fb39253828195d165f0b6d96f4a927ee6d2bc8cd972e44b1ab21
3
+ size 24414768512
superhot-30b-8k-prototype-v2.ggmlv3.Q5_K_M.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ef8616cb41089b393ef8545f8a53e91ef2d696ae6164f93b141fab921cabdb
3
+ size 23046827392
superhot-30b-8k-prototype-v2.ggmlv3.Q5_K_S.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:545cfc7a9dd6a5ae6695dea0feda875ef3985b2868876c18bcbb4214cc4ddcc7
3
+ size 22395071872
superhot-30b-8k-prototype-v2.ggmlv3.Q6_K.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95aa0ee4dc058ea697fbd43ed2323bf07aaef3e57b8ab24080917722692e6aa6
3
+ size 26686927232
superhot-30b-8k-prototype-v2.ggmlv3.Q8_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b69af69774fe708c81d2dc06e87f0a954c80dee4edbc0364113362ab67a2c8d7
3
+ size 34513251712