bnjmnmarie
commited on
Commit
•
38765f2
1
Parent(s):
a7432d5
Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ license: apache-2.0
|
|
12 |
|
13 |
This is [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) quantized with AutoRound (asymmetric quantization) to 4-bit. The model has been created, tested, and evaluated by The Kaitchup. It is compatible with the main inference frameworks, e.g., TGI and vLLM.
|
14 |
|
15 |
-
Details on quantization process and evaluation:
|
16 |
[Mistral-NeMo: 4.1x Smaller with Quantized Minitron](https://kaitchup.substack.com/p/mistral-nemo-41x-smaller-with-quantized)
|
17 |
|
18 |
|
|
|
12 |
|
13 |
This is [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) quantized with AutoRound (asymmetric quantization) to 4-bit. The model has been created, tested, and evaluated by The Kaitchup. It is compatible with the main inference frameworks, e.g., TGI and vLLM.
|
14 |
|
15 |
+
Details on the quantization process and evaluation:
|
16 |
[Mistral-NeMo: 4.1x Smaller with Quantized Minitron](https://kaitchup.substack.com/p/mistral-nemo-41x-smaller-with-quantized)
|
17 |
|
18 |
|