nm-testing
/

TinyLlama-1.1B-Chat-v1.0-W8A8_channel_weight_static_per_tensor-e2e

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

compressed-tensors

Model card Files Files and versions Community

dsikka commited on Aug 28

Commit

3472f87

•

1 Parent(s): 946eeb7

Upload LlamaForCausalLM

Files changed (2) hide show

config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/dsikka/.cache/huggingface/hub/models--TinyLlama--TinyLlama-1.1B-Chat-v1.0/snapshots/fe8a4ea1ffedaf415f4da2f062534de366a451e6",
   "architectures": [
     "LlamaForCausalLM"
   ],

 {
+  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--TinyLlama--TinyLlama-1.1B-Chat-v1.0/snapshots/fe8a4ea1ffedaf415f4da2f062534de366a451e6",
   "architectures": [
     "LlamaForCausalLM"
   ],

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9431a505d3b5ea7b6dfaab9f4381d463654f463b4f2a1ebb0fda32bfadc660cb
 size 1232059012

 version https://git-lfs.github.com/spec/v1
+oid sha256:a6e7dd01f726bae94988a632b681bcdbbfe122ae602b680c5a207f21a9c93f7e
 size 1232059012