Hugging Face's logo

Devops-hestabit
/
mixtral-instruct-trt

Model card Files Community
Devops-hestabit commited on
Commit
4c71db6
·
verified ·
1 Parent(s): 88372d7

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. postprocessing/1/__pycache__/model.cpython-310.pyc +0 -0
  2. postprocessing/config.pbtxt +1 -1
  3. preprocessing/1/__pycache__/model.cpython-310.pyc +0 -0
  4. preprocessing/config.pbtxt +1 -1
  5. tensorrt_llm/1/config.json +1 -1
  6. tensorrt_llm/1/rank1.engine +2 -2
  7. tensorrt_llm_bls/1/__pycache__/model.cpython-310.pyc +0 -0
  8. tensorrt_llm_bls/1/lib/__pycache__/decode.cpython-310.pyc +0 -0
  9. tensorrt_llm_bls/1/lib/__pycache__/triton_decoder.cpython-310.pyc +0 -0
postprocessing/1/__pycache__/model.cpython-310.pyc CHANGED
Binary files a/postprocessing/1/__pycache__/model.cpython-310.pyc and b/postprocessing/1/__pycache__/model.cpython-310.pyc differ
 
postprocessing/config.pbtxt CHANGED
@@ -101,7 +101,7 @@ parameters {
101
  parameters {
102
  key: "skip_special_tokens"
103
  value: {
104
- string_value: "${skip_special_tokens}"
105
  }
106
  }
107
 
 
101
  parameters {
102
  key: "skip_special_tokens"
103
  value: {
104
+ string_value: "false"
105
  }
106
  }
107
 
preprocessing/1/__pycache__/model.cpython-310.pyc CHANGED
Binary files a/preprocessing/1/__pycache__/model.cpython-310.pyc and b/preprocessing/1/__pycache__/model.cpython-310.pyc differ
 
preprocessing/config.pbtxt CHANGED
@@ -144,7 +144,7 @@ parameters {
144
  parameters {
145
  key: "add_special_tokens"
146
  value: {
147
- string_value: "${add_special_tokens}"
148
  }
149
  }
150
 
 
144
  parameters {
145
  key: "add_special_tokens"
146
  value: {
147
+ string_value: "false"
148
  }
149
  }
150
 
tensorrt_llm/1/config.json CHANGED
@@ -129,7 +129,7 @@
129
  "context_fmha_fp32_acc": false,
130
  "paged_kv_cache": true,
131
  "remove_input_padding": true,
132
- "use_custom_all_reduce": true,
133
  "reduce_fusion": false,
134
  "multi_block_mode": false,
135
  "enable_xqa": true,
 
129
  "context_fmha_fp32_acc": false,
130
  "paged_kv_cache": true,
131
  "remove_input_padding": true,
132
+ "use_custom_all_reduce": false,
133
  "reduce_fusion": false,
134
  "multi_block_mode": false,
135
  "enable_xqa": true,
tensorrt_llm/1/rank1.engine CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1397dbb8fc710907448a5c58da6c17004b8b8fa398780b1e593b383e6b150b6f
3
- size 46857271996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cce3cc78a466ba00ef6b65fafa85a18c8e8c177b8445ece1ce1d8539e764fcbb
3
+ size 46857273788
tensorrt_llm_bls/1/__pycache__/model.cpython-310.pyc CHANGED
Binary files a/tensorrt_llm_bls/1/__pycache__/model.cpython-310.pyc and b/tensorrt_llm_bls/1/__pycache__/model.cpython-310.pyc differ
 
tensorrt_llm_bls/1/lib/__pycache__/decode.cpython-310.pyc CHANGED
Binary files a/tensorrt_llm_bls/1/lib/__pycache__/decode.cpython-310.pyc and b/tensorrt_llm_bls/1/lib/__pycache__/decode.cpython-310.pyc differ
 
tensorrt_llm_bls/1/lib/__pycache__/triton_decoder.cpython-310.pyc CHANGED
Binary files a/tensorrt_llm_bls/1/lib/__pycache__/triton_decoder.cpython-310.pyc and b/tensorrt_llm_bls/1/lib/__pycache__/triton_decoder.cpython-310.pyc differ