Hugging Face's logo

second-state
/
Bielik-4.5B-v3.0-Instruct-GGUF

Text Generation
Transformers
GGUF
Polish
llama
conversational
Model card Files Community
apepkuss79 commited on
Commit
5ed9534
·
verified ·
1 Parent(s): fb073d4

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -64,23 +64,23 @@ inference:
64
  --prompt-template chatml \
65
  --ctx-size 32000
66
  ```
67
- <!--
68
  ## Quantized GGUF Models
69
 
70
  | Name | Quant method | Bits | Size | Use case |
71
  | ---- | ---- | ---- | ---- | ----- |
72
- | [Bielik-4.5B-v3.0-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q2_K.gguf) | Q2_K | 2 | 4.16 GB| smallest, significant quality loss - not recommended for most purposes |
73
- | [Bielik-4.5B-v3.0-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 5.88 GB| small, substantial quality loss |
74
- | [Bielik-4.5B-v3.0-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 5.40 GB| very small, high quality loss |
75
- | [Bielik-4.5B-v3.0-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 4.85 GB| very small, high quality loss |
76
- | [Bielik-4.5B-v3.0-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q4_0.gguf) | Q4_0 | 4 | 6.32 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
77
- | [Bielik-4.5B-v3.0-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 6.72 GB| medium, balanced quality - recommended |
78
- | [Bielik-4.5B-v3.0-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 6.36 GB| small, greater quality loss |
79
- | [Bielik-4.5B-v3.0-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q5_0.gguf) | Q5_0 | 5 | 7.70 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
80
- | [Bielik-4.5B-v3.0-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 7.91 GB| large, very low quality loss - recommended |
81
- | [Bielik-4.5B-v3.0-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 7.70 GB| large, low quality loss - recommended |
82
- | [Bielik-4.5B-v3.0-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q6_K.gguf) | Q6_K | 6 | 9.16 GB| very large, extremely low quality loss |
83
- | [Bielik-4.5B-v3.0-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q8_0.gguf) | Q8_0 | 8 | 11.9 GB| very large, extremely low quality loss - not recommended |
84
- | [Bielik-4.5B-v3.0-Instruct-f16.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-f16.gguf) | f16 | 16 | 22.3 GB| | -->
85
 
86
  *Quantized with llama.cpp b5201*
 
64
  --prompt-template chatml \
65
  --ctx-size 32000
66
  ```
67
+
68
  ## Quantized GGUF Models
69
 
70
  | Name | Quant method | Bits | Size | Use case |
71
  | ---- | ---- | ---- | ---- | ----- |
72
+ | [Bielik-4.5B-v3.0-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q2_K.gguf) | Q2_K | 2 | 1.77 GB| smallest, significant quality loss - not recommended for most purposes |
73
+ | [Bielik-4.5B-v3.0-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 2.50 GB| small, substantial quality loss |
74
+ | [Bielik-4.5B-v3.0-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 2.30 GB| very small, high quality loss |
75
+ | [Bielik-4.5B-v3.0-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 2.08 GB| very small, high quality loss |
76
+ | [Bielik-4.5B-v3.0-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q4_0.gguf) | Q4_0 | 4 | 2.70 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
77
+ | [Bielik-4.5B-v3.0-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 2.88 GB| medium, balanced quality - recommended |
78
+ | [Bielik-4.5B-v3.0-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 2.72 GB| small, greater quality loss |
79
+ | [Bielik-4.5B-v3.0-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q5_0.gguf) | Q5_0 | 5 | 3.29 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
80
+ | [Bielik-4.5B-v3.0-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 3.38 GB| large, very low quality loss - recommended |
81
+ | [Bielik-4.5B-v3.0-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 3.29 GB| large, low quality loss - recommended |
82
+ | [Bielik-4.5B-v3.0-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q6_K.gguf) | Q6_K | 6 | 3.91 GB| very large, extremely low quality loss |
83
+ | [Bielik-4.5B-v3.0-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-Q8_0.gguf) | Q8_0 | 8 | 5.06 GB| very large, extremely low quality loss - not recommended |
84
+ | [Bielik-4.5B-v3.0-Instruct-f16.gguf](https://huggingface.co/second-state/Bielik-4.5B-v3.0-Instruct-GGUF/blob/main/Bielik-4.5B-v3.0-Instruct-f16.gguf) | f16 | 16 | 9.52 GB| |
85
 
86
  *Quantized with llama.cpp b5201*