Hugging Face's logo

tensorblock
/
X-ALMA-13B-Pretrain-GGUF

GGUF
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
edac28b
•
1 Parent(s): fe7bdb5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -12
README.md CHANGED
@@ -78,8 +78,16 @@ This repo contains GGUF format model files for [haoranxu/X-ALMA-13B-Pretrain](ht
78
 
79
  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).
80
 
 
 
 
 
 
 
 
81
  ## Prompt template
82
 
 
83
  ```
84
  <s>[INST] <<SYS>>
85
  {system_prompt}
@@ -92,18 +100,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
92
 
93
  | Filename | Quant type | File Size | Description |
94
  | -------- | ---------- | --------- | ----------- |
95
- | [X-ALMA-13B-Pretrain-Q2_K.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q2_K.gguf) | Q2_K | 4.521 GB | smallest, significant quality loss - not recommended for most purposes |
96
- | [X-ALMA-13B-Pretrain-Q3_K_S.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q3_K_S.gguf) | Q3_K_S | 5.270 GB | very small, high quality loss |
97
- | [X-ALMA-13B-Pretrain-Q3_K_M.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q3_K_M.gguf) | Q3_K_M | 5.903 GB | very small, high quality loss |
98
- | [X-ALMA-13B-Pretrain-Q3_K_L.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q3_K_L.gguf) | Q3_K_L | 6.454 GB | small, substantial quality loss |
99
- | [X-ALMA-13B-Pretrain-Q4_0.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q4_0.gguf) | Q4_0 | 6.860 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
100
- | [X-ALMA-13B-Pretrain-Q4_K_S.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q4_K_S.gguf) | Q4_K_S | 6.913 GB | small, greater quality loss |
101
- | [X-ALMA-13B-Pretrain-Q4_K_M.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q4_K_M.gguf) | Q4_K_M | 7.326 GB | medium, balanced quality - recommended |
102
- | [X-ALMA-13B-Pretrain-Q5_0.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q5_0.gguf) | Q5_0 | 8.356 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
103
- | [X-ALMA-13B-Pretrain-Q5_K_S.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q5_K_S.gguf) | Q5_K_S | 8.356 GB | large, low quality loss - recommended |
104
- | [X-ALMA-13B-Pretrain-Q5_K_M.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q5_K_M.gguf) | Q5_K_M | 8.596 GB | large, very low quality loss - recommended |
105
- | [X-ALMA-13B-Pretrain-Q6_K.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q6_K.gguf) | Q6_K | 9.946 GB | very large, extremely low quality loss |
106
- | [X-ALMA-13B-Pretrain-Q8_0.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/tree/main/X-ALMA-13B-Pretrain-Q8_0.gguf) | Q8_0 | 12.881 GB | very large, extremely low quality loss - not recommended |
107
 
108
 
109
  ## Downloading instruction
 
78
 
79
  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).
80
 
81
+
82
+ <div style="text-align: left; margin: 20px 0;">
83
+ <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;">
84
+ Run them on the TensorBlock client using your local machine ↗
85
+ </a>
86
+ </div>
87
+
88
  ## Prompt template
89
 
90
+
91
  ```
92
  <s>[INST] <<SYS>>
93
  {system_prompt}
 
100
 
101
  | Filename | Quant type | File Size | Description |
102
  | -------- | ---------- | --------- | ----------- |
103
+ | [X-ALMA-13B-Pretrain-Q2_K.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q2_K.gguf) | Q2_K | 4.521 GB | smallest, significant quality loss - not recommended for most purposes |
104
+ | [X-ALMA-13B-Pretrain-Q3_K_S.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q3_K_S.gguf) | Q3_K_S | 5.270 GB | very small, high quality loss |
105
+ | [X-ALMA-13B-Pretrain-Q3_K_M.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q3_K_M.gguf) | Q3_K_M | 5.903 GB | very small, high quality loss |
106
+ | [X-ALMA-13B-Pretrain-Q3_K_L.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q3_K_L.gguf) | Q3_K_L | 6.454 GB | small, substantial quality loss |
107
+ | [X-ALMA-13B-Pretrain-Q4_0.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q4_0.gguf) | Q4_0 | 6.860 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
108
+ | [X-ALMA-13B-Pretrain-Q4_K_S.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q4_K_S.gguf) | Q4_K_S | 6.913 GB | small, greater quality loss |
109
+ | [X-ALMA-13B-Pretrain-Q4_K_M.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q4_K_M.gguf) | Q4_K_M | 7.326 GB | medium, balanced quality - recommended |
110
+ | [X-ALMA-13B-Pretrain-Q5_0.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q5_0.gguf) | Q5_0 | 8.356 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
111
+ | [X-ALMA-13B-Pretrain-Q5_K_S.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q5_K_S.gguf) | Q5_K_S | 8.356 GB | large, low quality loss - recommended |
112
+ | [X-ALMA-13B-Pretrain-Q5_K_M.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q5_K_M.gguf) | Q5_K_M | 8.596 GB | large, very low quality loss - recommended |
113
+ | [X-ALMA-13B-Pretrain-Q6_K.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q6_K.gguf) | Q6_K | 9.946 GB | very large, extremely low quality loss |
114
+ | [X-ALMA-13B-Pretrain-Q8_0.gguf](https://huggingface.co/tensorblock/X-ALMA-13B-Pretrain-GGUF/blob/main/X-ALMA-13B-Pretrain-Q8_0.gguf) | Q8_0 | 12.881 GB | very large, extremely low quality loss - not recommended |
115
 
116
 
117
  ## Downloading instruction