nm-testing
/

TinyLlama-1.1B-Chat-v1.0-W8A8-e2e

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

compressed-tensors

Model card Files Files and versions Community

nm-autobot commited on 29 days ago

Commit

3799633

•

1 Parent(s): 6944bc0

Upload LlamaForCausalLM

Files changed (2) hide show

config.json +2 -2
generation_config.json +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--TinyLlama--TinyLlama-1.1B-Chat-v1.0/snapshots/fe8a4ea1ffedaf415f4da2f062534de366a451e6",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -66,7 +66,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.2",
   "use_cache": true,
   "vocab_size": 32000
 }

 {
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json CHANGED Viewed

@@ -3,5 +3,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "4.46.2"
 }

   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
+  "transformers_version": "4.46.3"
 }