Hugging Face's logo

cszhzleo
/
Meta-Llama-3.1-8B-Instruct-nc2-bs1-token4096-neuron-220

Safetensors
llama
Model card Files Community
cszhzleo commited on
Commit
a804089
·
verified ·
1 Parent(s): decb4b1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -3,17 +3,20 @@ license: mit
3
  ---
4
  ### environment
5
  optimum-neuron 0.0.25.dev0
 
6
  neuron 2.20.0
 
7
  transformers-neuronx 0.12.313
 
8
  transformers 4.43.2
 
 
9
  ### export
10
  ```
11
  optimum-cli export neuron --model NousResearch/Meta-Llama-3.1-8B-Instruct --batch_size 1 --sequence_length 4096 --num_cores 2 --auto_cast_type fp16 ./models-hf/NousResearch/Meta-Llama-3.1-8B-Instruct
12
 
13
  ```
14
 
15
-
16
-
17
  ### run
18
  ```
19
  docker run -it --name llama-31 --rm \
 
3
  ---
4
  ### environment
5
  optimum-neuron 0.0.25.dev0
6
+
7
  neuron 2.20.0
8
+
9
  transformers-neuronx 0.12.313
10
+
11
  transformers 4.43.2
12
+
13
+
14
  ### export
15
  ```
16
  optimum-cli export neuron --model NousResearch/Meta-Llama-3.1-8B-Instruct --batch_size 1 --sequence_length 4096 --num_cores 2 --auto_cast_type fp16 ./models-hf/NousResearch/Meta-Llama-3.1-8B-Instruct
17
 
18
  ```
19
 
 
 
20
  ### run
21
  ```
22
  docker run -it --name llama-31 --rm \