Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
| 3 |
-
- mistralai/Mistral-Small-24B-Instruct-2501
|
| 4 |
library_name: transformers
|
| 5 |
license: apache-2.0
|
| 6 |
---
|
|
@@ -9,12 +8,6 @@ license: apache-2.0
|
|
| 9 |
|
| 10 |
**Arcee-Blitz (24B)** is a new Mistral-based 24B model distilled from DeepSeek, designed to be both **fast and efficient**. We view it as a practical “workhorse” model that can tackle a range of tasks without the overhead of larger architectures.
|
| 11 |
|
| 12 |
-
### Quantizations
|
| 13 |
-
|
| 14 |
-
GGUF quants are available [here](https://huggingface.co/arcee-ai/Arcee-Blitz-GGUF)
|
| 15 |
-
|
| 16 |
-
AWQ quants are available [here](https://huggingface.co/arcee-ai/Arcee-Blitz-AWQ)
|
| 17 |
-
|
| 18 |
### Model Details
|
| 19 |
|
| 20 |
- Architecture Base: Mistral-Small-24B-Instruct-2501
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: arcee-ai/Arcee-Blitz
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
license: apache-2.0
|
| 5 |
---
|
|
|
|
| 8 |
|
| 9 |
**Arcee-Blitz (24B)** is a new Mistral-based 24B model distilled from DeepSeek, designed to be both **fast and efficient**. We view it as a practical “workhorse” model that can tackle a range of tasks without the overhead of larger architectures.
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
### Model Details
|
| 12 |
|
| 13 |
- Architecture Base: Mistral-Small-24B-Instruct-2501
|