初始化项目，由ModelHub XC社区提供模型
Model: bartowski/THUDM_GLM-4-9B-0414-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
72
.gitattributes
vendored
Normal file
72
.gitattributes
vendored
Normal file
@@ -0,0 +1,72 @@
|
||||
*.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
|
||||
*.gguf* 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
|
||||
THUDM_GLM-4-9B-0414.imatrix filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
THUDM_GLM-4-9B-0414-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
176
README.md
Normal file
176
README.md
Normal file
@@ -0,0 +1,176 @@
|
||||
---
|
||||
quantized_by: bartowski
|
||||
pipeline_tag: text-generation
|
||||
language:
|
||||
- zh
|
||||
- en
|
||||
license: mit
|
||||
base_model: THUDM/GLM-4-9B-0414
|
||||
base_model_relation: quantized
|
||||
---
|
||||
|
||||
## Llamacpp imatrix Quantizations of GLM-4-9B-0414 by THUDM
|
||||
|
||||
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5228">b5228</a> for quantization.
|
||||
|
||||
Original model: https://huggingface.co/THUDM/GLM-4-9B-0414
|
||||
|
||||
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
|
||||
|
||||
```
|
||||
[gMASK]<sop><|system|>
|
||||
{system_prompt}<|user|>
|
||||
{prompt}<|assistant|>
|
||||
```
|
||||
|
||||
## What's new:
|
||||
|
||||
Fix tokenizer
|
||||
|
||||
## Download a file (not the whole branch) from below:
|
||||
|
||||
| Filename | Quant type | File Size | Split | Description |
|
||||
| -------- | ---------- | --------- | ----- | ----------- |
|
||||
| [GLM-4-9B-0414-bf16.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-bf16.gguf) | bf16 | 18.81GB | false | Full BF16 weights. |
|
||||
| [GLM-4-9B-0414-Q8_0.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q8_0.gguf) | Q8_0 | 10.00GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||
| [GLM-4-9B-0414-Q6_K_L.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q6_K_L.gguf) | Q6_K_L | 8.57GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||
| [GLM-4-9B-0414-Q6_K.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q6_K.gguf) | Q6_K | 8.27GB | false | Very high quality, near perfect, *recommended*. |
|
||||
| [GLM-4-9B-0414-Q5_K_L.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q5_K_L.gguf) | Q5_K_L | 7.43GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||
| [GLM-4-9B-0414-Q5_K_M.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q5_K_M.gguf) | Q5_K_M | 7.05GB | false | High quality, *recommended*. |
|
||||
| [GLM-4-9B-0414-Q5_K_S.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q5_K_S.gguf) | Q5_K_S | 6.70GB | false | High quality, *recommended*. |
|
||||
| [GLM-4-9B-0414-Q4_K_L.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q4_K_L.gguf) | Q4_K_L | 6.63GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||
| [GLM-4-9B-0414-Q4_K_M.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q4_K_M.gguf) | Q4_K_M | 6.17GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||
| [GLM-4-9B-0414-Q4_1.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q4_1.gguf) | Q4_1 | 6.01GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||
| [GLM-4-9B-0414-Q4_K_S.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q4_K_S.gguf) | Q4_K_S | 5.76GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||
| [GLM-4-9B-0414-Q3_K_XL.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q3_K_XL.gguf) | Q3_K_XL | 5.74GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
|
||||
| [GLM-4-9B-0414-Q4_0.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q4_0.gguf) | Q4_0 | 5.48GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||
| [GLM-4-9B-0414-IQ4_NL.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-IQ4_NL.gguf) | IQ4_NL | 5.47GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||
| [GLM-4-9B-0414-IQ4_XS.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-IQ4_XS.gguf) | IQ4_XS | 5.26GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||
| [GLM-4-9B-0414-Q3_K_L.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q3_K_L.gguf) | Q3_K_L | 5.20GB | false | Lower quality but usable, good for low RAM availability. |
|
||||
| [GLM-4-9B-0414-Q3_K_M.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q3_K_M.gguf) | Q3_K_M | 4.97GB | false | Low quality. |
|
||||
| [GLM-4-9B-0414-IQ3_M.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-IQ3_M.gguf) | IQ3_M | 4.72GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||
| [GLM-4-9B-0414-Q2_K_L.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q2_K_L.gguf) | Q2_K_L | 4.61GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||
| [GLM-4-9B-0414-Q3_K_S.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q3_K_S.gguf) | Q3_K_S | 4.59GB | false | Low quality, not recommended. |
|
||||
| [GLM-4-9B-0414-IQ3_XS.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-IQ3_XS.gguf) | IQ3_XS | 4.41GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||
| [GLM-4-9B-0414-IQ3_XXS.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-IQ3_XXS.gguf) | IQ3_XXS | 4.23GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||
| [GLM-4-9B-0414-Q2_K.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-Q2_K.gguf) | Q2_K | 4.01GB | false | Very low quality but surprisingly usable. |
|
||||
| [GLM-4-9B-0414-IQ2_M.gguf](https://huggingface.co/bartowski/THUDM_GLM-4-9B-0414-GGUF/blob/main/THUDM_GLM-4-9B-0414-IQ2_M.gguf) | IQ2_M | 3.95GB | 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/THUDM_GLM-4-9B-0414-GGUF --include "THUDM_GLM-4-9B-0414-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/THUDM_GLM-4-9B-0414-GGUF --include "THUDM_GLM-4-9B-0414-Q8_0/*" --local-dir ./
|
||||
```
|
||||
|
||||
You can either specify a new local-dir (THUDM_GLM-4-9B-0414-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, 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
|
||||
3
THUDM_GLM-4-9B-0414-IQ2_M.gguf
Normal file
3
THUDM_GLM-4-9B-0414-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c2b96ccbb2f674f60b672191f4beeb68a433264dec38b6124689030417058863
|
||||
size 3946313088
|
||||
3
THUDM_GLM-4-9B-0414-IQ3_M.gguf
Normal file
3
THUDM_GLM-4-9B-0414-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3473c34a3d95c4e1e471896850b1243d01dc0d0d77b568363b84bfa8fb8f6dec
|
||||
size 4721800576
|
||||
3
THUDM_GLM-4-9B-0414-IQ3_XS.gguf
Normal file
3
THUDM_GLM-4-9B-0414-IQ3_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d619395c61df952f527dc8c956e56e18db21e254789a0ca16df07b2ddb45b220
|
||||
size 4406408576
|
||||
3
THUDM_GLM-4-9B-0414-IQ3_XXS.gguf
Normal file
3
THUDM_GLM-4-9B-0414-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:82909b3b3673f8750599db35e45829a14f4ff206384004489afe7c37d072866c
|
||||
size 4226807168
|
||||
3
THUDM_GLM-4-9B-0414-IQ4_NL.gguf
Normal file
3
THUDM_GLM-4-9B-0414-IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ea23ab9fe9758715a42c5f2c99f1c27ac3c720146bbadef5c3599df970442cd2
|
||||
size 5465175424
|
||||
3
THUDM_GLM-4-9B-0414-IQ4_XS.gguf
Normal file
3
THUDM_GLM-4-9B-0414-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c85b661ed11c36f8b5a4f75da8bc1672b011febf8d71f098feab41186ad1767e
|
||||
size 5262275968
|
||||
3
THUDM_GLM-4-9B-0414-Q2_K.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8f6ad4ae6d9bb4cca4de34694211bc669bf8df1e71b69c4c2629fc8608ecf1bf
|
||||
size 4006344064
|
||||
3
THUDM_GLM-4-9B-0414-Q2_K_L.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q2_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:487cab46b3ecaaeb95b1dc9e085dec5d6d5dbbbda2964a68af77cc41132637fc
|
||||
size 4612552064
|
||||
3
THUDM_GLM-4-9B-0414-Q3_K_L.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:36c5dd25a85660d040d6d28a4398fc636d5d59521bcab3552e05720f99a0b8a7
|
||||
size 5196608896
|
||||
3
THUDM_GLM-4-9B-0414-Q3_K_M.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bac1470340530679564b3c3b670494387f996004603a3af619c484fb18515f55
|
||||
size 4974507392
|
||||
3
THUDM_GLM-4-9B-0414-Q3_K_S.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f2385616559e8ed2314c501dc5f6a85f7c8348d02ee38ef4a4ff592eda02160c
|
||||
size 4592039296
|
||||
3
THUDM_GLM-4-9B-0414-Q3_K_XL.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q3_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4f0d41f07bc51aeb0453a034a56a74c7963ef5343b65b4e4d6d8bbbe3d0025a6
|
||||
size 5739771264
|
||||
3
THUDM_GLM-4-9B-0414-Q4_0.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4996db1053041e801ca57e030a1ea3ad70b6d3eeb49573092313bd7776eecdf5
|
||||
size 5477463424
|
||||
3
THUDM_GLM-4-9B-0414-Q4_1.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:507ffe123f0e561a2f9c5dde84b3d23d8d9332a7e244e2b5cfb28e02eb81cc83
|
||||
size 6008599936
|
||||
3
THUDM_GLM-4-9B-0414-Q4_K_L.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q4_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f631f071e4e91789bbf362affbe0fd217625dd3054dec7aa078a2c7f2ff3da5f
|
||||
size 6627292544
|
||||
3
THUDM_GLM-4-9B-0414-Q4_K_M.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2b95f0b88eca423bfb874c4f8e7b9574ec76acab2befd272076e8a8dce31216a
|
||||
size 6166574464
|
||||
3
THUDM_GLM-4-9B-0414-Q4_K_S.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:edecb34f065c51223826618b35bb47da1d13f4d2fbddb3a99c51db46cb22bf95
|
||||
size 5758481792
|
||||
3
THUDM_GLM-4-9B-0414-Q5_K_L.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q5_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c43f4d4949504e1a13617269d40f3cb71a82e1c4d47817e372cf08704fbd7a9c
|
||||
size 7434040704
|
||||
3
THUDM_GLM-4-9B-0414-Q5_K_M.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:24013ada7a32e4e449e8aad7afb48261abb1c1d86be55506065c3676d0ad6742
|
||||
size 7050917248
|
||||
3
THUDM_GLM-4-9B-0414-Q5_K_S.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:29f7419db2f8e1e6ccb102aa5400f67c2d7c1553a7270705074b6c9f9eb3ee94
|
||||
size 6697514368
|
||||
3
THUDM_GLM-4-9B-0414-Q6_K.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b20636a8389d30295959b64df48e3e4a0de29ea00a6abb9be494bf1773858b7c
|
||||
size 8266642816
|
||||
3
THUDM_GLM-4-9B-0414-Q6_K_L.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q6_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:79c3818e023caa6e445f17eac85b741d4ce648cc5e4096dfdb8eef07a298c8c0
|
||||
size 8567321984
|
||||
3
THUDM_GLM-4-9B-0414-Q8_0.gguf
Normal file
3
THUDM_GLM-4-9B-0414-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7b4ea2795934ca05dc409251dddd289160a194a4d920b575d1de4516808bb50d
|
||||
size 9999611264
|
||||
3
THUDM_GLM-4-9B-0414-bf16.gguf
Normal file
3
THUDM_GLM-4-9B-0414-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:375fd89fc82886616ece3cdcdce9364983f54059cbb4ab1e027c1a171d5f1769
|
||||
size 18811581568
|
||||
3
THUDM_GLM-4-9B-0414.imatrix
Normal file
3
THUDM_GLM-4-9B-0414.imatrix
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6797698787046c9bb5ff6414fe58961e8dedb74da18e84fec02f1a84dd413410
|
||||
size 5476108
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
Reference in New Issue
Block a user