Update README.md
Browse files
README.md
CHANGED
@@ -70,7 +70,7 @@ We know that some people want to explore smaller models or don't have the resour
|
|
70 |
- Quanto - [4bit](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-Quanto-4bit), [8bit](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit)
|
71 |
- [FP8](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-FP8) (vLLM, SGLang - Ada Lovelace, Hopper optimized)
|
72 |
- [INT8 W8A8](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-W8A8) (vLLM INT8 quantization Weights=8bits and Activations=8bits)
|
73 |
-
- [GGUF - experimental - IQ imatrix IQ2_XXS, IQ3_XXS, IQ4_XS and calibrated Q4_K_M, Q5_K_M, Q6_K, Q8_0](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-GGUF-IQ-Imatrix)
|
74 |
|
75 |
Please note that quantized models may offer lower quality of generated answers compared to full sized variatns.
|
76 |
|
|
|
70 |
- Quanto - [4bit](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-Quanto-4bit), [8bit](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-Quanto-8bit)
|
71 |
- [FP8](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-FP8) (vLLM, SGLang - Ada Lovelace, Hopper optimized)
|
72 |
- [INT8 W8A8](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-W8A8) (vLLM INT8 quantization Weights=8bits and Activations=8bits)
|
73 |
+
- [GGUF - experimental - IQ imatrix IQ1_M, IQ2_XXS, IQ3_XXS, IQ4_XS and calibrated Q4_K_M, Q5_K_M, Q6_K, Q8_0](https://huggingface.co/speakleash/Bielik-11B-v2.2-Instruct-GGUF-IQ-Imatrix)
|
74 |
|
75 |
Please note that quantized models may offer lower quality of generated answers compared to full sized variatns.
|
76 |
|