auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,7 @@ quantized_by: mradermacher
|
|
| 12 |
gguf version of https://huggingface.co/tiiuae/falcon-40b-instruct
|
| 13 |
|
| 14 |
<!-- provided-files -->
|
|
|
|
| 15 |
## Usage
|
| 16 |
|
| 17 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
@@ -24,6 +25,20 @@ more details, including on how to concatenate multi-part files.
|
|
| 24 |
|
| 25 |
| Link | Type | Size/GB | Notes |
|
| 26 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
| [PART 1](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.SOURCE.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.SOURCE.gguf.part2of2) | SOURCE | 83.8 | source gguf, only provided when it was hard to come by |
|
| 28 |
|
| 29 |
|
|
|
|
| 12 |
gguf version of https://huggingface.co/tiiuae/falcon-40b-instruct
|
| 13 |
|
| 14 |
<!-- provided-files -->
|
| 15 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/falcon-40b-instruct-i1-GGUF
|
| 16 |
## Usage
|
| 17 |
|
| 18 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
|
| 25 |
|
| 26 |
| Link | Type | Size/GB | Notes |
|
| 27 |
|:-----|:-----|--------:|:------|
|
| 28 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.Q2_K.gguf) | Q2_K | 16.4 | |
|
| 29 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.IQ3_XS.gguf) | IQ3_XS | 18.4 | |
|
| 30 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.IQ3_S.gguf) | IQ3_S | 18.9 | fast, beats Q3_K* |
|
| 31 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.Q3_K_S.gguf) | Q3_K_S | 18.9 | |
|
| 32 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.IQ3_M.gguf) | IQ3_M | 19.8 | |
|
| 33 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.Q3_K_M.gguf) | Q3_K_M | 20.7 | lower quality |
|
| 34 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.Q3_K_L.gguf) | Q3_K_L | 22.2 | |
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.IQ4_XS.gguf) | IQ4_XS | 23.4 | |
|
| 36 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.Q4_K_S.gguf) | Q4_K_S | 24.4 | fast, medium quality |
|
| 37 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.Q4_K_M.gguf) | Q4_K_M | 26.1 | fast, medium quality |
|
| 38 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.Q5_K_S.gguf) | Q5_K_S | 29.6 | |
|
| 39 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.Q5_K_M.gguf) | Q5_K_M | 31.2 | |
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.Q6_K.gguf) | Q6_K | 35.1 | very good quality |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.Q8_0.gguf) | Q8_0 | 45.1 | fast, best quality |
|
| 42 |
| [PART 1](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.SOURCE.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/falcon-40b-instruct-GGUF/resolve/main/falcon-40b-instruct.SOURCE.gguf.part2of2) | SOURCE | 83.8 | source gguf, only provided when it was hard to come by |
|
| 43 |
|
| 44 |
|