Update README.md
Browse files
README.md
CHANGED
@@ -1,8 +1,3 @@
|
|
1 |
-
|
2 |
-
This quant was made for [infermatic.ai](https://infermatic.ai/)
|
3 |
-
|
4 |
-
Dynamic FP8 quant of [goliath-120b-Instruct-FP8-Dynamic](https://huggingface.co/alpindale/goliath-120b) made with AutoFP8.
|
5 |
-
|
6 |
---
|
7 |
license: llama2
|
8 |
language:
|
@@ -11,6 +6,12 @@ pipeline_tag: conversational
|
|
11 |
tags:
|
12 |
- merge
|
13 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
# Goliath 120B
|
15 |
|
16 |
An auto-regressive causal LM created by combining 2x finetuned [Llama-2 70B](https://huggingface.co/meta-llama/llama-2-70b-hf) into one.
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: llama2
|
3 |
language:
|
|
|
6 |
tags:
|
7 |
- merge
|
8 |
---
|
9 |
+
|
10 |
+
This quant was made for [infermatic.ai](https://infermatic.ai/)
|
11 |
+
|
12 |
+
Dynamic FP8 quant of [goliath-120b-Instruct-FP8-Dynamic](https://huggingface.co/alpindale/goliath-120b) made with AutoFP8.
|
13 |
+
|
14 |
+
|
15 |
# Goliath 120B
|
16 |
|
17 |
An auto-regressive causal LM created by combining 2x finetuned [Llama-2 70B](https://huggingface.co/meta-llama/llama-2-70b-hf) into one.
|