Hugging Face's logo

steerapi
/
Llama-2-7b-chat-hf-onnx-awq

Text Generation
Transformers
ONNX
llama
Inference Endpoints
Model card Files Community
1
steerapi commited on
Commit
fe0212f
·
1 Parent(s): 62f6e98

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. generation_config.json +3 -2
  3. onnx/decoder_model_merged_quantized.onnx +1 -1
  4. onnx/decoder_model_merged_quantized.onnx.data +3 -0
  5. onnx/decoder_model_merged_quantized.onnx_data +1 -1
.gitattributes CHANGED
@@ -41,3 +41,4 @@ decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
41
  decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
42
  decoder_model_merged_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
43
  decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
 
 
41
  decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
42
  decoder_model_merged_quantized.onnx_data filter=lfs diff=lfs merge=lfs -text
43
  decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
44
+ onnx/decoder_model_merged_quantized.onnx.data filter=lfs diff=lfs merge=lfs -text
generation_config.json CHANGED
@@ -1,9 +1,10 @@
1
  {
2
  "bos_token_id": 1,
 
3
  "eos_token_id": 2,
4
  "max_length": 4096,
5
  "pad_token_id": 0,
6
- "temperature": 0.9,
7
- "top_p": 0.6,
8
  "transformers_version": "4.31.0"
9
  }
 
1
  {
2
  "bos_token_id": 1,
3
+ "do_sample": true,
4
  "eos_token_id": 2,
5
  "max_length": 4096,
6
  "pad_token_id": 0,
7
+ "temperature": 0.6,
8
+ "top_p": 0.9,
9
  "transformers_version": "4.31.0"
10
  }
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1266c653f7026aa4126cac8eadae4eb82e617e37ed65cd60bfda5a490dcd305
3
  size 19045741
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cb113b61ec37aeb46e87871b6c6f73d5f24b79cdf0de2a32324b9fb3efdf22e
3
  size 19045741
onnx/decoder_model_merged_quantized.onnx.data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e67790077d6d3e66eb4320b47b360975332f52937c248c2c6d721b93266b2a
3
+ size 6739214336
onnx/decoder_model_merged_quantized.onnx_data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f57f92dce820666b27faace4a325a7d8d41691b4f9d3e3540ba70e696b42a06
3
  size 6739214336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e67790077d6d3e66eb4320b47b360975332f52937c248c2c6d721b93266b2a
3
  size 6739214336