Hugging Face's logo

tensorblock
/
Infinity-Instruct-3M-0625-Mistral-7B-GGUF

GGUF
English
TensorBlock
GGUF
conversational
Model card Files
xet
 Community
morriszms commited on
Commit
4e650e8
·
verified ·
1 Parent(s): fec0595

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -12
README.md CHANGED
@@ -27,8 +27,16 @@ This repo contains GGUF format model files for [BAAI/Infinity-Instruct-3M-0625-M
27
 
28
  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).
29
 
 
 
 
 
 
 
 
30
  ## Prompt template
31
 
 
32
  ```
33
  <|im_start|>system
34
  {system_prompt}<|im_end|>
@@ -41,18 +49,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
41
 
42
  | Filename | Quant type | File Size | Description |
43
  | -------- | ---------- | --------- | ----------- |
44
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q2_K.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q2_K.gguf) | Q2_K | 2.533 GB | smallest, significant quality loss - not recommended for most purposes |
45
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
46
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
47
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
48
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q4_0.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
49
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
50
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
51
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q5_0.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
52
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
53
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
54
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q6_K.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
55
- | [Infinity-Instruct-3M-0625-Mistral-7B-Q8_0.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/tree/main/Infinity-Instruct-3M-0625-Mistral-7B-Q8_0.gguf) | Q8_0 | 7.167 GB | very large, extremely low quality loss - not recommended |
56
 
57
 
58
  ## Downloading instruction
 
27
 
28
  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).
29
 
30
+
31
+ <div style="text-align: left; margin: 20px 0;">
32
+ <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;">
33
+ Run them on the TensorBlock client using your local machine ↗
34
+ </a>
35
+ </div>
36
+
37
  ## Prompt template
38
 
39
+
40
  ```
41
  <|im_start|>system
42
  {system_prompt}<|im_end|>
 
49
 
50
  | Filename | Quant type | File Size | Description |
51
  | -------- | ---------- | --------- | ----------- |
52
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q2_K.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q2_K.gguf) | Q2_K | 2.533 GB | smallest, significant quality loss - not recommended for most purposes |
53
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_S.gguf) | Q3_K_S | 2.947 GB | very small, high quality loss |
54
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_M.gguf) | Q3_K_M | 3.277 GB | very small, high quality loss |
55
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q3_K_L.gguf) | Q3_K_L | 3.560 GB | small, substantial quality loss |
56
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q4_0.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q4_0.gguf) | Q4_0 | 3.827 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
57
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q4_K_S.gguf) | Q4_K_S | 3.856 GB | small, greater quality loss |
58
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q4_K_M.gguf) | Q4_K_M | 4.068 GB | medium, balanced quality - recommended |
59
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q5_0.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q5_0.gguf) | Q5_0 | 4.654 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
60
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q5_K_S.gguf) | Q5_K_S | 4.654 GB | large, low quality loss - recommended |
61
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q5_K_M.gguf) | Q5_K_M | 4.779 GB | large, very low quality loss - recommended |
62
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q6_K.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q6_K.gguf) | Q6_K | 5.534 GB | very large, extremely low quality loss |
63
+ | [Infinity-Instruct-3M-0625-Mistral-7B-Q8_0.gguf](https://huggingface.co/tensorblock/Infinity-Instruct-3M-0625-Mistral-7B-GGUF/blob/main/Infinity-Instruct-3M-0625-Mistral-7B-Q8_0.gguf) | Q8_0 | 7.167 GB | very large, extremely low quality loss - not recommended |
64
 
65
 
66
  ## Downloading instruction