Hugging Face's logo

ChristianAzinn
/
gte-base-gguf

Feature Extraction
sentence-transformers
GGUF
English
mteb
bert
sentence-similarity
Sentence Transformers
Model card Files Community
ChristianAzinn commited on
Commit
8cf9843
·
verified ·
1 Parent(s): c379e58

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -60,20 +60,20 @@ Refer to the Provided Files table below to see what files use which methods, and
60
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
61
  | ---- | ---- | ---- | ---- | ---- | ----- |
62
  | Name | Quant method | Bits | Size | Use case |
63
- | [gte-base.Q2_K.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q2_K.gguf) | Q2_K | 2 | 144 MB | smallest, significant quality loss - not recommended for most purposes |
64
- | [gte-base.Q3_K_S.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q3_K_S.gguf) | Q3_K_S | 3 | 160 MB | very small, high quality loss |
65
- | [gte-base.Q3_K_M.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q3_K_M.gguf) | Q3_K_M | 3 | 181 MB | very small, high quality loss |
66
- | [gte-base.Q3_K_L.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q3_K_L.gguf) | Q3_K_L | 3 | 198 MB | small, substantial quality loss |
67
- | [gte-base.Q4_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q4_0.gguf) | Q4_0 | 4 | 200 MB | legacy; small, very high quality loss - prefer using Q3_K_M |
68
- | [gte-base.Q4_K_S.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q4_K_S.gguf) | Q4_K_S | 4 | 203 MB | small, greater quality loss |
69
- | [gte-base.Q4_K_M.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q4_K_M.gguf) | Q4_K_M | 4 | 216 MB | medium, balanced quality - recommended |
70
- | [gte-base.Q5_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q5_0.gguf) | Q5_0 | 5 | 237 MB | legacy; medium, balanced quality - prefer using Q4_K_M |
71
- | [gte-base.Q5_K_S.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q5_K_S.gguf) | Q5_K_S | 5 | 237 MB | large, low quality loss - recommended |
72
- | [gte-base.Q5_K_M.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q5_K_M.gguf) | Q5_K_M | 5 | 246 MB | large, very low quality loss - recommended |
73
- | [gte-base.Q6_K.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q6_K.gguf) | Q6_K | 6 | 278 MB | very large, extremely low quality loss |
74
- | [gte-base.Q8_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q8_0.gguf) | Q8_0 | 8 | 358 MB | very large, extremely low quality loss - recommended |
75
- | [gte-base.Q8_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base_fp16.gguf) | FP16 | 16 | 670 MB | enormous, pretty much the original model - not recommended |
76
- | [gte-base.Q8_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base_fp32.gguf) | FP32 | 32 | 1.34 GB | enormous, pretty much the original model - not recommended |
77
 
78
  # Examples
79
  ## Example Usage with `llama.cpp`
 
60
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
61
  | ---- | ---- | ---- | ---- | ---- | ----- |
62
  | Name | Quant method | Bits | Size | Use case |
63
+ | [gte-base.Q2_K.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q2_K.gguf) | Q2_K | 2 | 54.2 MB | smallest, significant quality loss - not recommended for most purposes |
64
+ | [gte-base.Q3_K_S.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q3_K_S.gguf) | Q3_K_S | 3 | 58.5 MB | very small, high quality loss |
65
+ | [gte-base.Q3_K_M.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q3_K_M.gguf) | Q3_K_M | 3 | 64.6 MB | very small, high quality loss |
66
+ | [gte-base.Q3_K_L.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q3_K_L.gguf) | Q3_K_L | 3 | 69.5 MB | small, substantial quality loss |
67
+ | [gte-base.Q4_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q4_0.gguf) | Q4_0 | 4 | 69.8 MB | legacy; small, very high quality loss - prefer using Q3_K_M |
68
+ | [gte-base.Q4_K_S.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q4_K_S.gguf) | Q4_K_S | 4 | 71 MB | small, greater quality loss |
69
+ | [gte-base.Q4_K_M.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q4_K_M.gguf) | Q4_K_M | 4 | 74.4 MB | medium, balanced quality - recommended |
70
+ | [gte-base.Q5_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q5_0.gguf) | Q5_0 | 5 | 80.4 MB | legacy; medium, balanced quality - prefer using Q4_K_M |
71
+ | [gte-base.Q5_K_S.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q5_K_S.gguf) | Q5_K_S | 5 | 80/4 MB | large, low quality loss - recommended |
72
+ | [gte-base.Q5_K_M.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q5_K_M.gguf) | Q5_K_M | 5 | 82.8 MB | large, very low quality loss - recommended |
73
+ | [gte-base.Q6_K.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q6_K.gguf) | Q6_K | 6 | 91.7 MB | very large, extremely low quality loss |
74
+ | [gte-base.Q8_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base.Q8_0.gguf) | Q8_0 | 8 | 118 MB | very large, extremely low quality loss - recommended |
75
+ | [gte-base.Q8_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base_fp16.gguf) | FP16 | 16 | 219 MB | enormous, pretty much the original model - not recommended |
76
+ | [gte-base.Q8_0.gguf](https://huggingface.co/ChristianAzinn/gte-base-gguf/blob/main/gte-base_fp32.gguf) | FP32 | 32 | 436 MB | enormous, pretty much the original model - not recommended |
77
 
78
  # Examples
79
  ## Example Usage with `llama.cpp`