readme: add model card
Browse files
README.md
CHANGED
|
@@ -1,3 +1,24 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: llama3.1
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3.1
|
| 3 |
+
library_name: ggml
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Meta-Llama-3.1-405B-Instruct-GGUF
|
| 7 |
+
|
| 8 |
+
Low bit quantizations of Meta's Llama 3.1 405B Instruct model. Quantized from ollama q4_0 GGUF.
|
| 9 |
+
|
| 10 |
+
**Quants:**
|
| 11 |
+
- Q2_K
|
| 12 |
+
- (imatrix)
|
| 13 |
+
- Q3_K_M
|
| 14 |
+
- Q3_K_S
|
| 15 |
+
- Q3_K_L
|
| 16 |
+
- Q4_K_M
|
| 17 |
+
- Q4_0
|
| 18 |
+
- Q4_K_S
|
| 19 |
+
|
| 20 |
+
imatrix calibration data: groups_merged.dat
|
| 21 |
+
|
| 22 |
+
## imatrix
|
| 23 |
+
|
| 24 |
+
Experimental, force quanted to iq1_m, then an imatrix is generated and quanted to iq1_m again, and that is used to generate the final imatrix for all quants.
|