Hugging Face's logo

pankajroark
/
llama-fp16-engine

Model card Files Community
pankajroark commited on
Commit
18b067e
·
1 Parent(s): bd472e5

update non-quant engine again, this time with one that is locally tested

Browse files
Files changed (2) hide show
  1. 7b-no-quant-tp1/llama_float16_tp1_rank0.engine +2 -2
  2. 7b-no-quant-tp1/model.cache +0 -0
7b-no-quant-tp1/llama_float16_tp1_rank0.engine CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44082abbf34483808729d46983500858093fddc8e4eb31c282471f93dba3fd33
3
- size 13480840252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a3503def50dac6e4803d433c80eacbf45d8f7127e7818935b5d373d2fa2b3d8
3
+ size 13480840124
7b-no-quant-tp1/model.cache CHANGED
Binary files a/7b-no-quant-tp1/model.cache and b/7b-no-quant-tp1/model.cache differ