Hugging Face's logo

tensorblock
/
Ko-Llama3-Luxia-8B-it-GGUF

GGUF
Korean
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
e94a401
•
1 Parent(s): f83b8b8

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +15 -17
README.md CHANGED
@@ -2,7 +2,7 @@
2
  license: llama3
3
  language:
4
  - ko
5
- base_model: lubocido/Ko-Llama3-Luxia-8B-it
6
  tags:
7
  - TensorBlock
8
  - GGUF
@@ -19,13 +19,12 @@ tags:
19
  </div>
20
  </div>
21
 
22
- ## lubocido/Ko-Llama3-Luxia-8B-it - GGUF
23
 
24
- This repo contains GGUF format model files for [lubocido/Ko-Llama3-Luxia-8B-it](https://huggingface.co/lubocido/Ko-Llama3-Luxia-8B-it).
25
 
26
  The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
27
 
28
-
29
  <div style="text-align: left; margin: 20px 0;">
30
  <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
31
  Run them on the TensorBlock client using your local machine ↗
@@ -34,7 +33,6 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
34
 
35
  ## Prompt template
36
 
37
-
38
  ```
39
  {system_prompt}{prompt}
40
  ```
@@ -43,18 +41,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
43
 
44
  | Filename | Quant type | File Size | Description |
45
  | -------- | ---------- | --------- | ----------- |
46
- | [Ko-Llama3-Luxia-8B-it-Q2_K.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q2_K.gguf) | Q2_K | 3.038 GB | smallest, significant quality loss - not recommended for most purposes |
47
- | [Ko-Llama3-Luxia-8B-it-Q3_K_S.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q3_K_S.gguf) | Q3_K_S | 3.497 GB | very small, high quality loss |
48
- | [Ko-Llama3-Luxia-8B-it-Q3_K_M.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q3_K_M.gguf) | Q3_K_M | 3.827 GB | very small, high quality loss |
49
- | [Ko-Llama3-Luxia-8B-it-Q3_K_L.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q3_K_L.gguf) | Q3_K_L | 4.110 GB | small, substantial quality loss |
50
- | [Ko-Llama3-Luxia-8B-it-Q4_0.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q4_0.gguf) | Q4_0 | 4.434 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
51
- | [Ko-Llama3-Luxia-8B-it-Q4_K_S.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q4_K_S.gguf) | Q4_K_S | 4.464 GB | small, greater quality loss |
52
- | [Ko-Llama3-Luxia-8B-it-Q4_K_M.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q4_K_M.gguf) | Q4_K_M | 4.676 GB | medium, balanced quality - recommended |
53
- | [Ko-Llama3-Luxia-8B-it-Q5_0.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q5_0.gguf) | Q5_0 | 5.316 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
54
- | [Ko-Llama3-Luxia-8B-it-Q5_K_S.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q5_K_S.gguf) | Q5_K_S | 5.316 GB | large, low quality loss - recommended |
55
- | [Ko-Llama3-Luxia-8B-it-Q5_K_M.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q5_K_M.gguf) | Q5_K_M | 5.441 GB | large, very low quality loss - recommended |
56
- | [Ko-Llama3-Luxia-8B-it-Q6_K.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q6_K.gguf) | Q6_K | 6.254 GB | very large, extremely low quality loss |
57
- | [Ko-Llama3-Luxia-8B-it-Q8_0.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q8_0.gguf) | Q8_0 | 8.097 GB | very large, extremely low quality loss - not recommended |
58
 
59
 
60
  ## Downloading instruction
 
2
  license: llama3
3
  language:
4
  - ko
5
+ base_model: ludobico/Ko-Llama3-Luxia-8B-it
6
  tags:
7
  - TensorBlock
8
  - GGUF
 
19
  </div>
20
  </div>
21
 
22
+ ## ludobico/Ko-Llama3-Luxia-8B-it - GGUF
23
 
24
+ This repo contains GGUF format model files for [ludobico/Ko-Llama3-Luxia-8B-it](https://huggingface.co/ludobico/Ko-Llama3-Luxia-8B-it).
25
 
26
  The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
27
 
 
28
  <div style="text-align: left; margin: 20px 0;">
29
  <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
30
  Run them on the TensorBlock client using your local machine ↗
 
33
 
34
  ## Prompt template
35
 
 
36
  ```
37
  {system_prompt}{prompt}
38
  ```
 
41
 
42
  | Filename | Quant type | File Size | Description |
43
  | -------- | ---------- | --------- | ----------- |
44
+ | [Ko-Llama3-Luxia-8B-it-Q2_K.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q2_K.gguf) | Q2_K | 3.263 GB | smallest, significant quality loss - not recommended for most purposes |
45
+ | [Ko-Llama3-Luxia-8B-it-Q3_K_S.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q3_K_S.gguf) | Q3_K_S | 3.755 GB | very small, high quality loss |
46
+ | [Ko-Llama3-Luxia-8B-it-Q3_K_M.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q3_K_M.gguf) | Q3_K_M | 4.110 GB | very small, high quality loss |
47
+ | [Ko-Llama3-Luxia-8B-it-Q3_K_L.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q3_K_L.gguf) | Q3_K_L | 4.413 GB | small, substantial quality loss |
48
+ | [Ko-Llama3-Luxia-8B-it-Q4_0.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q4_0.gguf) | Q4_0 | 4.761 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
49
+ | [Ko-Llama3-Luxia-8B-it-Q4_K_S.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q4_K_S.gguf) | Q4_K_S | 4.793 GB | small, greater quality loss |
50
+ | [Ko-Llama3-Luxia-8B-it-Q4_K_M.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q4_K_M.gguf) | Q4_K_M | 5.021 GB | medium, balanced quality - recommended |
51
+ | [Ko-Llama3-Luxia-8B-it-Q5_0.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q5_0.gguf) | Q5_0 | 5.708 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
52
+ | [Ko-Llama3-Luxia-8B-it-Q5_K_S.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q5_K_S.gguf) | Q5_K_S | 5.708 GB | large, low quality loss - recommended |
53
+ | [Ko-Llama3-Luxia-8B-it-Q5_K_M.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q5_K_M.gguf) | Q5_K_M | 5.842 GB | large, very low quality loss - recommended |
54
+ | [Ko-Llama3-Luxia-8B-it-Q6_K.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q6_K.gguf) | Q6_K | 6.715 GB | very large, extremely low quality loss |
55
+ | [Ko-Llama3-Luxia-8B-it-Q8_0.gguf](https://huggingface.co/tensorblock/Ko-Llama3-Luxia-8B-it-GGUF/blob/main/Ko-Llama3-Luxia-8B-it-Q8_0.gguf) | Q8_0 | 8.694 GB | very large, extremely low quality loss - not recommended |
56
 
57
 
58
  ## Downloading instruction