robgreenberg3 commited on
Commit
8d83bb9
·
verified ·
1 Parent(s): 5272ac7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -8
README.md CHANGED
@@ -1,10 +1,4 @@
1
  ---
2
- tags:
3
- - int8
4
- - vllm
5
- - chat
6
- - neuralmagic
7
- - llmcompressor
8
  language:
9
  - en
10
  - de
@@ -14,9 +8,31 @@ language:
14
  - hi
15
  - es
16
  - th
 
 
17
  pipeline_tag: text-generation
18
- license: llama3.3
19
- base_model: meta-llama/Llama-3.3-70B-Instruct
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  ---
21
  <h1 style="display: flex; align-items: center; gap: 10px; margin: 0;">
22
  Llama-3.3-70B-Instruct-quantized.w8a8
 
1
  ---
 
 
 
 
 
 
2
  language:
3
  - en
4
  - de
 
8
  - hi
9
  - es
10
  - th
11
+ base_model:
12
+ - meta-llama/Llama-3.3-70B-Instruct
13
  pipeline_tag: text-generation
14
+ tags:
15
+ - llama
16
+ - facebook
17
+ - meta
18
+ - llama-3
19
+ - int8
20
+ - vllm
21
+ - chat
22
+ - neuralmagic
23
+ - llmcompressor
24
+ - conversational
25
+ - 8-bit precision
26
+ - compressed-tensors
27
+ license: other
28
+ license_name: llama3.3
29
+ name: RedHatAI/Llama-3.3-70B-Instruct-quantized.w8a8
30
+ description: This model was obtained by quantizing the weights and activations of Llama-3.3-70B-Instruct to INT8 data type.
31
+ readme: https://huggingface.co/RedHatAI/Llama-3.3-70B-Instruct-quantized.w8a8/main/README.md
32
+ tasks:
33
+ - text-to-text
34
+ provider: Meta
35
+ license_link: https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE
36
  ---
37
  <h1 style="display: flex; align-items: center; gap: 10px; margin: 0;">
38
  Llama-3.3-70B-Instruct-quantized.w8a8