初始化项目，由ModelHub XC社区提供模型
Model: bartowski/ibm-granite_granite-4.0-h-tiny-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
73
.gitattributes
vendored
Normal file
73
.gitattributes
vendored
Normal file
@@ -0,0 +1,73 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
ibm-granite_granite-4.0-h-tiny-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
164
README.md
Normal file
164
README.md
Normal file
@@ -0,0 +1,164 @@
|
|||||||
|
---
|
||||||
|
quantized_by: bartowski
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
base_model_relation: quantized
|
||||||
|
base_model: ibm-granite/granite-4.0-h-tiny
|
||||||
|
---
|
||||||
|
|
||||||
|
## Llamacpp imatrix Quantizations of granite-4.0-h-tiny by ibm-granite
|
||||||
|
|
||||||
|
Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b6647">b6647</a> for quantization.
|
||||||
|
|
||||||
|
Original model: https://huggingface.co/ibm-granite/granite-4.0-h-tiny
|
||||||
|
|
||||||
|
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet)
|
||||||
|
|
||||||
|
Run them in [LM Studio](https://lmstudio.ai/)
|
||||||
|
|
||||||
|
Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project
|
||||||
|
|
||||||
|
## Prompt format
|
||||||
|
|
||||||
|
No prompt format found, check original model page
|
||||||
|
|
||||||
|
## Download a file (not the whole branch) from below:
|
||||||
|
|
||||||
|
| Filename | Quant type | File Size | Split | Description |
|
||||||
|
| -------- | ---------- | --------- | ----- | ----------- |
|
||||||
|
| [granite-4.0-h-tiny-bf16.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-bf16.gguf) | bf16 | 13.89GB | false | Full BF16 weights. |
|
||||||
|
| [granite-4.0-h-tiny-Q8_0.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q8_0.gguf) | Q8_0 | 7.39GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||||
|
| [granite-4.0-h-tiny-Q6_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q6_K_L.gguf) | Q6_K_L | 5.79GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||||
|
| [granite-4.0-h-tiny-Q6_K.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q6_K.gguf) | Q6_K | 5.76GB | false | Very high quality, near perfect, *recommended*. |
|
||||||
|
| [granite-4.0-h-tiny-Q5_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q5_K_L.gguf) | Q5_K_L | 5.05GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||||
|
| [granite-4.0-h-tiny-Q5_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q5_K_M.gguf) | Q5_K_M | 5.02GB | false | High quality, *recommended*. |
|
||||||
|
| [granite-4.0-h-tiny-Q5_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q5_K_S.gguf) | Q5_K_S | 4.86GB | false | High quality, *recommended*. |
|
||||||
|
| [granite-4.0-h-tiny-Q4_1.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q4_1.gguf) | Q4_1 | 4.44GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||||
|
| [granite-4.0-h-tiny-Q4_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q4_K_L.gguf) | Q4_K_L | 4.33GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||||
|
| [granite-4.0-h-tiny-Q4_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf) | Q4_K_M | 4.30GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||||
|
| [granite-4.0-h-tiny-Q4_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q4_K_S.gguf) | Q4_K_S | 4.15GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||||
|
| [granite-4.0-h-tiny-Q4_0.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q4_0.gguf) | Q4_0 | 4.09GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||||
|
| [granite-4.0-h-tiny-IQ4_NL.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ4_NL.gguf) | IQ4_NL | 4.02GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||||
|
| [granite-4.0-h-tiny-IQ4_XS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ4_XS.gguf) | IQ4_XS | 3.82GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||||
|
| [granite-4.0-h-tiny-Q3_K_XL.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q3_K_XL.gguf) | Q3_K_XL | 3.45GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
|
||||||
|
| [granite-4.0-h-tiny-Q3_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q3_K_L.gguf) | Q3_K_L | 3.41GB | false | Lower quality but usable, good for low RAM availability. |
|
||||||
|
| [granite-4.0-h-tiny-Q3_K_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q3_K_M.gguf) | Q3_K_M | 3.29GB | false | Low quality. |
|
||||||
|
| [granite-4.0-h-tiny-IQ3_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ3_M.gguf) | IQ3_M | 3.29GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||||
|
| [granite-4.0-h-tiny-Q3_K_S.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q3_K_S.gguf) | Q3_K_S | 3.15GB | false | Low quality, not recommended. |
|
||||||
|
| [granite-4.0-h-tiny-IQ3_XS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ3_XS.gguf) | IQ3_XS | 3.01GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||||
|
| [granite-4.0-h-tiny-IQ3_XXS.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ3_XXS.gguf) | IQ3_XXS | 2.87GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||||
|
| [granite-4.0-h-tiny-Q2_K_L.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q2_K_L.gguf) | Q2_K_L | 2.62GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||||
|
| [granite-4.0-h-tiny-Q2_K.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-Q2_K.gguf) | Q2_K | 2.59GB | false | Very low quality but surprisingly usable. |
|
||||||
|
| [granite-4.0-h-tiny-IQ2_M.gguf](https://huggingface.co/bartowski/ibm-granite_granite-4.0-h-tiny-GGUF/blob/main/ibm-granite_granite-4.0-h-tiny-IQ2_M.gguf) | IQ2_M | 2.29GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
|
||||||
|
|
||||||
|
## Embed/output weights
|
||||||
|
|
||||||
|
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
|
||||||
|
|
||||||
|
## Downloading using huggingface-cli
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Click to view download instructions</summary>
|
||||||
|
|
||||||
|
First, make sure you have hugginface-cli installed:
|
||||||
|
|
||||||
|
```
|
||||||
|
pip install -U "huggingface_hub[cli]"
|
||||||
|
```
|
||||||
|
|
||||||
|
Then, you can target the specific file you want:
|
||||||
|
|
||||||
|
```
|
||||||
|
huggingface-cli download bartowski/ibm-granite_granite-4.0-h-tiny-GGUF --include "ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf" --local-dir ./
|
||||||
|
```
|
||||||
|
|
||||||
|
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
|
||||||
|
|
||||||
|
```
|
||||||
|
huggingface-cli download bartowski/ibm-granite_granite-4.0-h-tiny-GGUF --include "ibm-granite_granite-4.0-h-tiny-Q8_0/*" --local-dir ./
|
||||||
|
```
|
||||||
|
|
||||||
|
You can either specify a new local-dir (ibm-granite_granite-4.0-h-tiny-Q8_0) or download them all in place (./)
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## ARM/AVX information
|
||||||
|
|
||||||
|
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
|
||||||
|
|
||||||
|
Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
|
||||||
|
|
||||||
|
As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
|
||||||
|
|
||||||
|
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Click to view Q4_0_X_X information (deprecated</summary>
|
||||||
|
|
||||||
|
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
|
||||||
|
|
||||||
|
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
|
||||||
|
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
|
||||||
|
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
|
||||||
|
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
|
||||||
|
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
|
||||||
|
|
||||||
|
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## Which file should I choose?
|
||||||
|
|
||||||
|
<details>
|
||||||
|
<summary>Click here for details</summary>
|
||||||
|
|
||||||
|
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
|
||||||
|
|
||||||
|
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
|
||||||
|
|
||||||
|
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
|
||||||
|
|
||||||
|
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
|
||||||
|
|
||||||
|
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
|
||||||
|
|
||||||
|
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
|
||||||
|
|
||||||
|
If you want to get more into the weeds, you can check out this extremely useful feature chart:
|
||||||
|
|
||||||
|
[llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix)
|
||||||
|
|
||||||
|
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
|
||||||
|
|
||||||
|
These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
|
||||||
|
|
||||||
|
</details>
|
||||||
|
|
||||||
|
## Credits
|
||||||
|
|
||||||
|
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
|
||||||
|
|
||||||
|
Thank you ZeroWw for the inspiration to experiment with embed/output.
|
||||||
|
|
||||||
|
Thank you to LM Studio for sponsoring my work.
|
||||||
|
|
||||||
|
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
3
ibm-granite_granite-4.0-h-tiny-IQ2_M.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:06f75822f83db56e9b66dd46ec7c845f68312df10259f33bce56d2d83527d9d8
|
||||||
|
size 2291237952
|
||||||
3
ibm-granite_granite-4.0-h-tiny-IQ3_M.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:49f6587da93654c50f6c3c6d572fe380363c279fd840f1b49e3cdae3b7a892a7
|
||||||
|
size 3285037632
|
||||||
3
ibm-granite_granite-4.0-h-tiny-IQ3_XS.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-IQ3_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:408595ac18fea857a2398ba135738883262ef837ce0ce610a313838b508e33c9
|
||||||
|
size 3008926272
|
||||||
3
ibm-granite_granite-4.0-h-tiny-IQ3_XXS.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3429ad758378097a5173e78ec1bc5cc81611a33c1ec571d87862af1f8b4351b9
|
||||||
|
size 2868669504
|
||||||
3
ibm-granite_granite-4.0-h-tiny-IQ4_NL.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4257dd9c4f20bbe64bccc9643b479a9bfba91e5a0c74b752868c916a7f4042db
|
||||||
|
size 4024673088
|
||||||
3
ibm-granite_granite-4.0-h-tiny-IQ4_XS.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:761bf97b24d7386f4f814f92ad53bba55aaad1b612b4a1023d604d1358cc353c
|
||||||
|
size 3819085632
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q2_K.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:873f7d981dea6555f855759559e963ed73d04a1cd9b98cb9f799da2d5addf1eb
|
||||||
|
size 2585322816
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q2_K_L.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q2_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:643663be82267e81a17e2aefb9e84515751fccb476e21a799821f8d2c08dc91a
|
||||||
|
size 2622653760
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q3_K_L.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7884ea5ca8d834782c5ce12eac5c082d42df6ee088f1e97e7bf86e1e60829c9d
|
||||||
|
size 3408826944
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q3_K_M.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9cb3b2e61565c811c183a3ad3f5398703feca907c1ef30f8c77ad6c54b62756b
|
||||||
|
size 3285234240
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q3_K_S.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cd89fd0214f4730405084afd43efd5652f8e62d20d52b821024a0a9f6b07af2e
|
||||||
|
size 3150926400
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q3_K_XL.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q3_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9dae381645f8c956cdf52325c936c37084c64e145c44e9902ac59953411b5745
|
||||||
|
size 3446157888
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q4_0.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:30eae42251c8b8c9d87326351255b55c6a328c492224dd7a28120bf064a28819
|
||||||
|
size 4086408000
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q4_1.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7190245c2ef70aa9ec84daceb94b4263a096127086798a69d34f55b9c496ad17
|
||||||
|
size 4435258176
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q4_K_L.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q4_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:82484a50c20e6b3072a7ed4d270f0198990bade447699ab45c344beeab4e600f
|
||||||
|
size 4334465856
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:33a689fe7f35b14ebab3ae599b65aaa3ed8548c393373b1b0eebee36c653146f
|
||||||
|
size 4297134912
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q4_K_S.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:571e43f86e3316a14af523e566fef5d48e8377803a9c44ace8af26cc88926d0a
|
||||||
|
size 4150895424
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q5_K_L.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q5_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cb3de6a22235772243d799b6f45262c1fe104a5f0561fb1364999954fc5ddf16
|
||||||
|
size 5053645632
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q5_K_M.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:dbf86daa13091ed5591b341d74b751f47b23242546998f62cf97d8355db4a70a
|
||||||
|
size 5016314688
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q5_K_S.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d915a1bccc4129d4d54a789562790b4f30933951e13c528afe14fa2917e84b0b
|
||||||
|
size 4859556672
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q6_K.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6c1c57e35d687b7ce24eb283c89d2ca7e2cf598d05521800329a8d62ce9e45ca
|
||||||
|
size 5757412416
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q6_K_L.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q6_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:156529c8f187a1405c1d766694c98faf4e022ef441d688840ef0a5a5ab6db097
|
||||||
|
size 5794743360
|
||||||
3
ibm-granite_granite-4.0-h-tiny-Q8_0.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:aa3799edad3bf487827a298f1cfbc26269ca4ee6fe87706efe76120a107d6787
|
||||||
|
size 7390331712
|
||||||
3
ibm-granite_granite-4.0-h-tiny-bf16.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3158f000b5991e49bca070457b354d5981bfd27dca68e536516a9e0fdeb76c99
|
||||||
|
size 13891205952
|
||||||
3
ibm-granite_granite-4.0-h-tiny-imatrix.gguf
Normal file
3
ibm-granite_granite-4.0-h-tiny-imatrix.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:309bc231f05cc5bf2c01478b31a69ad565767b89637714876e0ec2792211b66a
|
||||||
|
size 38451424
|
||||||
Reference in New Issue
Block a user