fix metadata
Browse files
README.md
CHANGED
|
@@ -7,6 +7,7 @@ tags:
|
|
| 7 |
- creative-writing
|
| 8 |
base_model:
|
| 9 |
- zai-org/GLM-4.6
|
|
|
|
| 10 |
pipeline_tag: text-generation
|
| 11 |
library_name: transformers
|
| 12 |
---
|
|
@@ -58,12 +59,3 @@ llama-server --model GLM-4.6-IQ3_KS-00001-of-00004.gguf [your usual CLI argument
|
|
| 58 |
### Limitations
|
| 59 |
|
| 60 |
With reasoning enabled on extreme quants like IQ2_XXS, very simple prompts like "Hi" may result in irrelevant replies.
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
**More Control-Vectors will be added as they're tested**
|
| 65 |
-
|
| 66 |
-
### TODO
|
| 67 |
-
- ~~upload after I get below the huggingface storage limit.~~
|
| 68 |
-
- upload assistant vectors after benchmarks completed.
|
| 69 |
-
- improve model card / documentation / acknowledgements.
|
|
|
|
| 7 |
- creative-writing
|
| 8 |
base_model:
|
| 9 |
- zai-org/GLM-4.6
|
| 10 |
+
base_model_relation: adapter
|
| 11 |
pipeline_tag: text-generation
|
| 12 |
library_name: transformers
|
| 13 |
---
|
|
|
|
| 59 |
### Limitations
|
| 60 |
|
| 61 |
With reasoning enabled on extreme quants like IQ2_XXS, very simple prompts like "Hi" may result in irrelevant replies.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|