Add metadata
Browse files
README.md
CHANGED
|
@@ -2,6 +2,15 @@
|
|
| 2 |
license: llama3.1
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
base_model: mattshumer/ref_70_e3
|
| 6 |
pipeline_tag: text-generation
|
| 7 |
library_name: ggml
|
|
@@ -22,22 +31,35 @@ GGUF quantized models of [mattshumer/ref_70_e3](https://huggingface.co/mattshume
|
|
| 22 |
| Quantization | Size | Split | iMatrix |
|
| 23 |
| ------------ | ------ | ----- | ------- |
|
| 24 |
| FP16 | 141GB | true | false |
|
| 25 |
-
| Q8_0_L |
|
| 26 |
-
|
|
|
|
|
| 27 |
| Q6_K | ??.?GB | true | false |
|
| 28 |
| Q5_K_L | 52.6GB | true | false |
|
| 29 |
| Q5_K_M | ??.?GB | true | false |
|
| 30 |
-
| Q5_K_S |
|
| 31 |
-
| Q4_K_L |
|
| 32 |
| Q4_K_M | ??.?GB | false | false |
|
| 33 |
| Q4_K_S | ??.?GB | false | false |
|
| 34 |
-
|
|
| 35 |
-
|
|
|
|
|
|
|
|
| 36 |
| Q3_K_M | ??.?GB | false | false |
|
|
|
|
| 37 |
| Q3_K_S | ??.?GB | false | false |
|
|
|
|
| 38 |
| Q2_K_L | 29.4GB | false | false |
|
|
|
|
|
|
|
| 39 |
| Q2_K | ??.?GB | false | false |
|
| 40 |
| Q2_K_S | ??.?GB | false | true |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
The `_L` or `_XL` suffix means that the token embeddings and output weight are at fp16 precision.
|
| 43 |
|
|
|
|
| 2 |
license: llama3.1
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
+
- de
|
| 6 |
+
- fr
|
| 7 |
+
- it
|
| 8 |
+
- pt
|
| 9 |
+
- hi
|
| 10 |
+
- es
|
| 11 |
+
- th
|
| 12 |
+
tags:
|
| 13 |
+
- llama
|
| 14 |
base_model: mattshumer/ref_70_e3
|
| 15 |
pipeline_tag: text-generation
|
| 16 |
library_name: ggml
|
|
|
|
| 31 |
| Quantization | Size | Split | iMatrix |
|
| 32 |
| ------------ | ------ | ----- | ------- |
|
| 33 |
| FP16 | 141GB | true | false |
|
| 34 |
+
| Q8_0_L | ??.?GB | true | false |
|
| 35 |
+
| Q8_0 | ??.?GB | true | false |
|
| 36 |
+
| Q6_K_L | ??.?GB | true | false |
|
| 37 |
| Q6_K | ??.?GB | true | false |
|
| 38 |
| Q5_K_L | 52.6GB | true | false |
|
| 39 |
| Q5_K_M | ??.?GB | true | false |
|
| 40 |
+
| Q5_K_S | 48.7GB | false | false |
|
| 41 |
+
| Q4_K_L | 45.3GB | false | false |
|
| 42 |
| Q4_K_M | ??.?GB | false | false |
|
| 43 |
| Q4_K_S | ??.?GB | false | false |
|
| 44 |
+
| IQ4_NL | ??.?GB | false | true |
|
| 45 |
+
| IQ4_XS | ??.?GB | false | true |
|
| 46 |
+
| Q3_K_XL | 37.2GB | false | false |
|
| 47 |
+
| Q3_K_L | ??.?GB | false | false |
|
| 48 |
| Q3_K_M | ??.?GB | false | false |
|
| 49 |
+
| IQ3_M | ??.?GB | false | true |
|
| 50 |
| Q3_K_S | ??.?GB | false | false |
|
| 51 |
+
| IQ3_S | ??.?GB | false | true |
|
| 52 |
| Q2_K_L | 29.4GB | false | false |
|
| 53 |
+
| IQ3_XS | ??.?GB | false | true |
|
| 54 |
+
| IQ3_XXS | ??.?GB | false | true |
|
| 55 |
| Q2_K | ??.?GB | false | false |
|
| 56 |
| Q2_K_S | ??.?GB | false | true |
|
| 57 |
+
| IQ2_M | ??.?GB | false | true |
|
| 58 |
+
| IQ2_S | ??.?GB | false | true |
|
| 59 |
+
| IQ2_XS | ??.?GB | false | true |
|
| 60 |
+
| IQ2_XXS | ??.?GB | false | true |
|
| 61 |
+
| IQ1_M | ??.?GB | false | true |
|
| 62 |
+
| IQ1_S | ??.?GB | false | true |
|
| 63 |
|
| 64 |
The `_L` or `_XL` suffix means that the token embeddings and output weight are at fp16 precision.
|
| 65 |
|