Update README.md
Browse files
README.md
CHANGED
|
@@ -3,12 +3,11 @@ inference: false
|
|
| 3 |
---
|
| 4 |
# weblab-10b-instruction-sft-GPTQ
|
| 5 |
|
| 6 |
-
original model [weblab-10b-instruction-sft](https://huggingface.co/matsuo-lab/weblab-10b-instruction-sft)
|
| 7 |
-
|
| 8 |
-
This is 4bit GPTQ Version.You need autoGPTQ library to use this model.
|
| 9 |
-
|
| 10 |
-
The size is smaller and the execution speed is faster, but the inference performance may be a little worse.
|
| 11 |
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
### sample code
|
| 14 |
At least one GPU is currently required due to a limitation of the Accelerate library.
|
|
|
|
| 3 |
---
|
| 4 |
# weblab-10b-instruction-sft-GPTQ
|
| 5 |
|
| 6 |
+
original model [weblab-10b-instruction-sft](https://huggingface.co/matsuo-lab/weblab-10b-instruction-sft) whith is a Japanese-centric multilingual GPT-NeoX model of 10 billion parameters.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
+
This model is 4bit GPTQ Version.
|
| 9 |
+
The size is smaller and the execution speed is faster, but the inference performance may be a little worse.
|
| 10 |
+
You need autoGPTQ library to use this model.
|
| 11 |
|
| 12 |
### sample code
|
| 13 |
At least one GPU is currently required due to a limitation of the Accelerate library.
|