Update README.md
Browse files
README.md
CHANGED
|
@@ -125,8 +125,16 @@ This repo contains GGUF format model files for [tiiuae/falcon-mamba-7b](https://
|
|
| 125 |
|
| 126 |
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).
|
| 127 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
## Prompt template
|
| 129 |
|
|
|
|
| 130 |
```
|
| 131 |
|
| 132 |
```
|
|
@@ -135,18 +143,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
|
|
| 135 |
|
| 136 |
| Filename | Quant type | File Size | Description |
|
| 137 |
| -------- | ---------- | --------- | ----------- |
|
| 138 |
-
| [falcon-mamba-7b-Q2_K.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 139 |
-
| [falcon-mamba-7b-Q3_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 140 |
-
| [falcon-mamba-7b-Q3_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 141 |
-
| [falcon-mamba-7b-Q3_K_L.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 142 |
-
| [falcon-mamba-7b-Q4_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 143 |
-
| [falcon-mamba-7b-Q4_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 144 |
-
| [falcon-mamba-7b-Q4_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 145 |
-
| [falcon-mamba-7b-Q5_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 146 |
-
| [falcon-mamba-7b-Q5_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 147 |
-
| [falcon-mamba-7b-Q5_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 148 |
-
| [falcon-mamba-7b-Q6_K.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 149 |
-
| [falcon-mamba-7b-Q8_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/
|
| 150 |
|
| 151 |
|
| 152 |
## Downloading instruction
|
|
|
|
| 125 |
|
| 126 |
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).
|
| 127 |
|
| 128 |
+
|
| 129 |
+
<div style="text-align: left; margin: 20px 0;">
|
| 130 |
+
<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;">
|
| 131 |
+
Run them on the TensorBlock client using your local machine ↗
|
| 132 |
+
</a>
|
| 133 |
+
</div>
|
| 134 |
+
|
| 135 |
## Prompt template
|
| 136 |
|
| 137 |
+
|
| 138 |
```
|
| 139 |
|
| 140 |
```
|
|
|
|
| 143 |
|
| 144 |
| Filename | Quant type | File Size | Description |
|
| 145 |
| -------- | ---------- | --------- | ----------- |
|
| 146 |
+
| [falcon-mamba-7b-Q2_K.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q2_K.gguf) | Q2_K | 2.389 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 147 |
+
| [falcon-mamba-7b-Q3_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q3_K_S.gguf) | Q3_K_S | 3.050 GB | very small, high quality loss |
|
| 148 |
+
| [falcon-mamba-7b-Q3_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q3_K_M.gguf) | Q3_K_M | 3.050 GB | very small, high quality loss |
|
| 149 |
+
| [falcon-mamba-7b-Q3_K_L.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q3_K_L.gguf) | Q3_K_L | 3.050 GB | small, substantial quality loss |
|
| 150 |
+
| [falcon-mamba-7b-Q4_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q4_0.gguf) | Q4_0 | 3.915 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 151 |
+
| [falcon-mamba-7b-Q4_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q4_K_S.gguf) | Q4_K_S | 3.915 GB | small, greater quality loss |
|
| 152 |
+
| [falcon-mamba-7b-Q4_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q4_K_M.gguf) | Q4_K_M | 3.915 GB | medium, balanced quality - recommended |
|
| 153 |
+
| [falcon-mamba-7b-Q5_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q5_0.gguf) | Q5_0 | 4.730 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 154 |
+
| [falcon-mamba-7b-Q5_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q5_K_S.gguf) | Q5_K_S | 4.730 GB | large, low quality loss - recommended |
|
| 155 |
+
| [falcon-mamba-7b-Q5_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q5_K_M.gguf) | Q5_K_M | 4.730 GB | large, very low quality loss - recommended |
|
| 156 |
+
| [falcon-mamba-7b-Q6_K.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q6_K.gguf) | Q6_K | 5.595 GB | very large, extremely low quality loss |
|
| 157 |
+
| [falcon-mamba-7b-Q8_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/blob/main/falcon-mamba-7b-Q8_0.gguf) | Q8_0 | 7.232 GB | very large, extremely low quality loss - not recommended |
|
| 158 |
|
| 159 |
|
| 160 |
## Downloading instruction
|