Update README.md: head 8bit
Browse files
README.md
CHANGED
@@ -27,7 +27,7 @@ datasets:
|
|
27 |
base_model: CausalLM/35b-beta-long
|
28 |
---
|
29 |
|
30 |
-
# Exllamav2 Quant of CausalLM/35b-beta-long, 4.0bpw (fits into 24GiB VRAM with 8192 context and 4bit KV cache)
|
31 |
|
32 |
**Sorry, it's no longer available on Hugging Face. Please reach out to those who have already downloaded it. If you have a copy, please refrain from re-uploading it to Hugging Face.**
|
33 |
|
|
|
27 |
base_model: CausalLM/35b-beta-long
|
28 |
---
|
29 |
|
30 |
+
# Exllamav2 Quant of CausalLM/35b-beta-long, 4.0bpw h8 (fits into 24GiB VRAM with 8192 context and 4bit KV cache)
|
31 |
|
32 |
**Sorry, it's no longer available on Hugging Face. Please reach out to those who have already downloaded it. If you have a copy, please refrain from re-uploading it to Hugging Face.**
|
33 |
|