bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-12 18:33:12 +08:00
commit 64693bed25
28 changed files with 319 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
.gitattributes vendored Normal file
View File

@@ -0,0 +1,60 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt 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
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz 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
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl 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
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* 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
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-f16.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-f32.gguf filter=lfs diff=lfs merge=lfs -text
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO.imatrix filter=lfs diff=lfs merge=lfs -text

183
README.md Normal file
View File

@@ -0,0 +1,183 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
license: other
base_model: fblgit/miniclaus-qw1.5B-UNAMGS-GRPO
tags:
- generated_from_trainer
language:
- en
license_name: qwen
license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
datasets:
- Magpie-Align/Magpie-Pro-MT-300K-v0.1
model-index:
- name: miniclaus-qw1.5B-UNAMGS
results: []
---
## Llamacpp imatrix Quantizations of miniclaus-qw1.5B-UNAMGS-GRPO by fblgit
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4585">b4585</a> for quantization.
Original model: https://huggingface.co/fblgit/miniclaus-qw1.5B-UNAMGS-GRPO
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
## Prompt format
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [miniclaus-qw1.5B-UNAMGS-GRPO-f32.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-f32.gguf) | f32 | 6.18GB | false | Full F32 weights. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-f16.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-f16.gguf) | f16 | 3.09GB | false | Full F16 weights. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q8_0.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q8_0.gguf) | Q8_0 | 1.65GB | false | Extremely high quality, generally unneeded but max available quant. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q6_K_L.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q6_K_L.gguf) | Q6_K_L | 1.33GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q6_K.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q6_K.gguf) | Q6_K | 1.27GB | false | Very high quality, near perfect, *recommended*. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_L.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_L.gguf) | Q5_K_L | 1.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_M.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_M.gguf) | Q5_K_M | 1.13GB | false | High quality, *recommended*. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_S.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_S.gguf) | Q5_K_S | 1.10GB | false | High quality, *recommended*. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_L.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_L.gguf) | Q4_K_L | 1.04GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q4_1.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_1.gguf) | Q4_1 | 1.02GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_M.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_M.gguf) | Q4_K_M | 0.99GB | false | Good quality, default size for most use cases, *recommended*. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_S.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_S.gguf) | Q4_K_S | 0.94GB | false | Slightly lower quality with more space savings, *recommended*. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q4_0.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_0.gguf) | Q4_0 | 0.94GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-IQ4_NL.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ4_NL.gguf) | IQ4_NL | 0.94GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_XL.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_XL.gguf) | Q3_K_XL | 0.94GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-IQ4_XS.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ4_XS.gguf) | IQ4_XS | 0.90GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_L.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_L.gguf) | Q3_K_L | 0.88GB | false | Lower quality but usable, good for low RAM availability. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_M.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_M.gguf) | Q3_K_M | 0.82GB | false | Low quality. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-IQ3_M.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ3_M.gguf) | IQ3_M | 0.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_S.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_S.gguf) | Q3_K_S | 0.76GB | false | Low quality, not recommended. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-IQ3_XS.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ3_XS.gguf) | IQ3_XS | 0.73GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q2_K_L.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q2_K_L.gguf) | Q2_K_L | 0.73GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-Q2_K.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q2_K.gguf) | Q2_K | 0.68GB | false | Very low quality but surprisingly usable. |
| [miniclaus-qw1.5B-UNAMGS-GRPO-IQ2_M.gguf](https://huggingface.co/bartowski/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF/blob/main/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ2_M.gguf) | IQ2_M | 0.60GB | 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/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF --include "fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-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/fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-GGUF --include "fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-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/ggerganov/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/ggerganov/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/ggerganov/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/ggerganov/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 and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
</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
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:19d40bee8567e969f37bd62145b994958e8fee71d20d0c3550401efc7f1fed30
size 601055264

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:527071aad445b3a89d1f0d93b983f7eef8d942b503713db84ea43ae12545a7ad
size 776664608

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:13eef37d2e00c99e92f7aa1f3c8c5bcd913a634907c049ec6cb137e8c14e242b
size 731699744

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0d906f82ef811fa42e71f8f4d8b4970018d1070a07d9e70668af659c02905f1c
size 936331808

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ab8316f6da1f7b89609c0f72fc7c91502d3a7b23b6d328e040610c3909c83953
size 895732256

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:525706bf6737cc7c889cbc0ac1fd140a87fe3394d7f439aff26aa0d941d28aa9
size 676305440

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:36ce80d71f47b5b67fb0fd89613a7f96fa58b4053079c98c7d3bdb7b8c56782a
size 732825632

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4e55e422045906edca46bf92c28fab398af6588f35633fc0732b43c1fffbfc0
size 880163360

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b1f42e3c56ca4bba438d0ff964bcc40251b41a0f17a80e45606dcf6400f4292
size 824179232

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:112ef6136fe4f229d594e98ad1ae7ee5875c4b968b92a110fa8693cc2cfced60
size 760945184

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a094e0fe43e1009c7276dd3aab3b56b716106cd0513c6a7b22b9b47d84e11fbb
size 936683552

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:029ab15a4c8666b99db0a47afe79bb7ff44a6f953a5771027fdfd9d42909afa7
size 937536032

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:82ccb9df9fd23605b3c2a46c7d35c38e29a10a7a7d9ad59c24221c1a34904a0d
size 1016842784

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e54b71ccbe3ecab191ccdb64db06d9cbd7e9bbc6a4f5dcdbfdfb29cb7d780572
size 1042569248

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:88ceacc5900062bc2afc352f009233225b0fe10203cbb61b122e8f10244449c8
size 986049056

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0e26f462209e67aa538762cbb0ad5943dc56536c455b037b83b11be415259f47
size 940313120

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:67d19fa77ab272a32c1278b7913c95a2b426fa6d53fb9dd6eaaae8d31c711603
size 1181571104

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:baabe1406f6b800782d5d07d15e11a43659a0d49ab1669b39b2a9c8cc98628d4
size 1125050912

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:42ce8357423a04290a3249d10dc502dc33295f13fd43060b4b8864c2d9d35a60
size 1098730016

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6fc08c07eaa5421e69e6ef3f43907682addf4d8320ca68758d2c4bea68221544
size 1272740384

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bcb82c6d36973f709a9def4104a1105a4a1a74125e4308f92b5ae3d4f71769e9
size 1329260576

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:15c3583746155101547ee6883cb4cb0abea1c17fb204cf9c75b31c9ed5b518bd
size 1646573600

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b3f2787e8acf329b3c32fe37d19aef62ea569bb719fbd7aa5d017f906f74fa1d
size 3093669920

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO-f32.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2a84619ad65cf7ba0313871a25c1d2a8492e301a2208899a4177741c45371737
size 6180808416

3
fblgit_miniclaus-qw1.5B-UNAMGS-GRPO.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3de40f0a9f6b60f7f603a5f5444508cf7043019175bdd4fc90b907f948a96275
size 2042214