michael
commited on
Commit
·
576a06b
1
Parent(s):
3558cdb
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- llama2
|
| 4 |
+
- llama-2-7b-chat-hf
|
| 5 |
+
---
|
| 6 |
+
# Llama-2-7b-chat-hf-GGUF
|
| 7 |
+
Based on Llama-2-7b-chat-hf.
|
| 8 |
+
|
| 9 |
+
GGML_VERSION = "gguf"
|
| 10 |
+
Conversion = float16
|
| 11 |
+
Quantization method = q4_k_s (Uses Q4_K for all tensors - "q" + the number of bits + the variant used )
|