Hugging Face's logo

dacorvo
/
tiny-random-gpt2-neuronx

Transformers
gpt2
Inference Endpoints
Model card Files Community
dacorvo HF staff commited on
Commit
6cb671b
•
1 Parent(s): d06efa1

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. compiled/657d574c80336c8465f9.neff +0 -0
  2. compiled/dd08d205e248ed14caa1.neff +0 -0
  3. compiled/fd4b8c88a732d6050a2b.neff +0 -0
  4. config.json +1 -1
compiled/657d574c80336c8465f9.neff ADDED
Binary file (175 kB). View file
 
compiled/dd08d205e248ed14caa1.neff ADDED
Binary file (165 kB). View file
 
compiled/fd4b8c88a732d6050a2b.neff ADDED
Binary file (206 kB). View file
 
config.json CHANGED
@@ -21,7 +21,7 @@
21
  "n_positions": 512,
22
  "neuron": {
23
  "auto_cast_type": "fp32",
24
- "batch_size": 1,
25
  "compiler_type": "neuronx-cc",
26
  "compiler_version": "2.11.0.31+b1624c454",
27
  "num_cores": 2,
 
21
  "n_positions": 512,
22
  "neuron": {
23
  "auto_cast_type": "fp32",
24
+ "batch_size": 16,
25
  "compiler_type": "neuronx-cc",
26
  "compiler_version": "2.11.0.31+b1624c454",
27
  "num_cores": 2,