Hugging Face's logo

tensorblock
/
Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF

GGUF
English
Chinese
axolotl
Generated from Trainer
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
d12e5d0
·
verified ·
1 Parent(s): d272d75

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -12
README.md CHANGED
@@ -35,8 +35,16 @@ This repo contains GGUF format model files for [Magpie-Align/Llama-3-8B-Magpie-A
35
 
36
  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).
37
 
 
 
 
 
 
 
 
38
  ## Prompt template
39
 
 
40
  ```
41
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>
42
 
@@ -49,18 +57,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
49
 
50
  | Filename | Quant type | File Size | Description |
51
  | -------- | ---------- | --------- | ----------- |
52
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
53
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
54
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
55
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
56
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
57
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
58
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
59
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
60
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
61
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
62
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
63
- | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/tree/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
64
 
65
 
66
  ## Downloading instruction
 
35
 
36
  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).
37
 
38
+
39
+ <div style="text-align: left; margin: 20px 0;">
40
+ <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;">
41
+ Run them on the TensorBlock client using your local machine ↗
42
+ </a>
43
+ </div>
44
+
45
  ## Prompt template
46
 
47
+
48
  ```
49
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>
50
 
 
57
 
58
  | Filename | Quant type | File Size | Description |
59
  | -------- | ---------- | --------- | ----------- |
60
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
61
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
62
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
63
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
64
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
65
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
66
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
67
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
68
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
69
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
70
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
71
+ | [Llama-3-8B-Magpie-Align-SFT-v0.3-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-Magpie-Align-SFT-v0.3-GGUF/blob/main/Llama-3-8B-Magpie-Align-SFT-v0.3-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
72
 
73
 
74
  ## Downloading instruction