初始化项目,由ModelHub XC社区提供模型

Model: bartowski/LongWriter-glm4-9b-abliterated-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC committed 2026-11-06 00:04:12 +08:00
commit c2a335ad60
28 files changed
+273

No files matched your search

+60
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
LongWriter-glm4-9b-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated-f16.gguf filter=lfs diff=lfs merge=lfs -text
LongWriter-glm4-9b-abliterated.imatrix filter=lfs diff=lfs merge=lfs -text
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b6342dc04cf52ded4b263158a2cac36d171c195c96b18dbc31a8aef01204656b
size 3931539936
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a78ae2e63af2464f24b0bcacebcd716d3be4071d0843750e8f7b2b2c2aa2d50e
size 4811885024
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5d8912a7eaca2862200c652a69b57fdf5726135af2217f68675f5479d11cf925
size 4429646304
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c0cc2aa7274532ed84a598de245fa7ffe6f033385b8a78facadc01e04f977697
size 5251107296
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e86c4e3c5e0fe093dedf9ab7bcce3bded4790f631371915228ab4994c07ead74
size 3991898592
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1d129436c3e3cd6ee707b20034144fce9eb9f1fb3991a2ca61be40fdd8a6243a
size 4598106592
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e53c1870880e6da98ab97f93623a1f346b5d6d1aada151bd1042f170d47b5720
size 5281450464
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:00c932f8e8b520bc49b92aa220d141b666b20c647254b7d1b203816ff274af7a
size 5064329696
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:25af8bb68fcd42c93ad662db4c87b217d4a68b5527b7cdca3bd55db2e960c9dc
size 4587424224
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bf29b03c0e520fe96c7ef9bb1f08b257c3e5fb6bebbb173555bb1034948ae4b7
size 5824612832
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8cfe0cd76d176b1bc83d0a301762309d08b1fce6a462c9b27ecece64365e2104
size 5472848352
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1854efc872fc234d5b60e4614bd3bc286c309bf3f43d44cc1bec49435f14de72
size 5455317472
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0d0e1c053a02219719ca793a1d5487e9fa32d348e207575b457e57d42946707a
size 5455317472
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a43c47d8e28a2f498dec8f4e7f00dd7653168c82935486d293bf9e7d168d6f36
size 5455317472
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:39ab497db4a1d0f80f16d0a79dd6bf34b24e0261c481edda0876475d80226c99
size 6711642592
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97f3967c433842eeb2eb96be75b34b2c9289fbcf0bf6dfc17178b4610b37ac14
size 6250924512
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3a831a04a1fce2e628bf084f5cb12e7e7b3decc90e8b91a2c6bdbae4db36505b
size 5753342432
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:311732867be77f26410bf2c8cbcba2e740c5551701d2d511655753e141b76f59
size 7526910432
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:92cd8a6d298e48d8994fb7eeb922621fe3c43fe3270c6506adbd9fd3b0c0924c
size 7143786976
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d42edcc7d10e71340ec01eab06e3e7035b9b3fd6297a59dda536bb6f1b9a17fd
size 6692899296
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d929c93ee19e47a09212425c3e39f7eeed17c145095c7b44d166495a35ad1f19
size 8262027744
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33c09c9b1c0bba8b1f136f7930c0aacc6e3afdd089d6ee4fef6921f945fe22e8
size 8562706912
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:26bd806ea03a0ac0aa868c740482970b798c13678f2578d6167b033d791f219e
size 9994996192
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:257f6ceb24a2c71a1d3bcafec54ac602739fb05c79c5810c69f9fb6e66398746
size 18806966464
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a5cc0a03c1d066be05a47705e53f9713a0ad163128e1a2878fec51ea738600ec
size 4162928
+137
View File
@@ -0,0 +1,137 @@
---
base_model: byroneverson/LongWriter-glm4-9b-abliterated
language:
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- llm
- glm
- glm4
- chatglm
- llama
- chat
- instruct
- it
- abliterated
- longwriter
- long context
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of LongWriter-glm4-9b-abliterated
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3930">b3930</a> for quantization.
Original model: https://huggingface.co/byroneverson/LongWriter-glm4-9b-abliterated
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
## Prompt format
```
[gMASK]<sop><|system|>
{system_prompt}<|user|>
{prompt}<|assistant|>
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [LongWriter-glm4-9b-abliterated-f16.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-f16.gguf) | f16 | 18.81GB | false | Full F16 weights. |
| [LongWriter-glm4-9b-abliterated-Q8_0.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q8_0.gguf) | Q8_0 | 9.99GB | false | Extremely high quality, generally unneeded but max available quant. |
| [LongWriter-glm4-9b-abliterated-Q6_K_L.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q6_K_L.gguf) | Q6_K_L | 8.56GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [LongWriter-glm4-9b-abliterated-Q6_K.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q6_K.gguf) | Q6_K | 8.26GB | false | Very high quality, near perfect, *recommended*. |
| [LongWriter-glm4-9b-abliterated-Q5_K_L.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q5_K_L.gguf) | Q5_K_L | 7.53GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [LongWriter-glm4-9b-abliterated-Q5_K_M.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q5_K_M.gguf) | Q5_K_M | 7.14GB | false | High quality, *recommended*. |
| [LongWriter-glm4-9b-abliterated-Q4_K_L.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q4_K_L.gguf) | Q4_K_L | 6.71GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [LongWriter-glm4-9b-abliterated-Q5_K_S.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q5_K_S.gguf) | Q5_K_S | 6.69GB | false | High quality, *recommended*. |
| [LongWriter-glm4-9b-abliterated-Q4_K_M.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q4_K_M.gguf) | Q4_K_M | 6.25GB | false | Good quality, default size for must use cases, *recommended*. |
| [LongWriter-glm4-9b-abliterated-Q3_K_XL.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q3_K_XL.gguf) | Q3_K_XL | 5.82GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [LongWriter-glm4-9b-abliterated-Q4_K_S.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q4_K_S.gguf) | Q4_K_S | 5.75GB | false | Slightly lower quality with more space savings, *recommended*. |
| [LongWriter-glm4-9b-abliterated-Q4_0.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q4_0.gguf) | Q4_0 | 5.47GB | false | Legacy format, generally not worth using over similarly sized formats |
| [LongWriter-glm4-9b-abliterated-Q4_0_8_8.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q4_0_8_8.gguf) | Q4_0_8_8 | 5.46GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
| [LongWriter-glm4-9b-abliterated-Q4_0_4_8.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q4_0_4_8.gguf) | Q4_0_4_8 | 5.46GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
| [LongWriter-glm4-9b-abliterated-Q4_0_4_4.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q4_0_4_4.gguf) | Q4_0_4_4 | 5.46GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. *Don't use on Mac or Windows*. |
| [LongWriter-glm4-9b-abliterated-Q3_K_L.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q3_K_L.gguf) | Q3_K_L | 5.28GB | false | Lower quality but usable, good for low RAM availability. |
| [LongWriter-glm4-9b-abliterated-IQ4_XS.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-IQ4_XS.gguf) | IQ4_XS | 5.25GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [LongWriter-glm4-9b-abliterated-Q3_K_M.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q3_K_M.gguf) | Q3_K_M | 5.06GB | false | Low quality. |
| [LongWriter-glm4-9b-abliterated-IQ3_M.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-IQ3_M.gguf) | IQ3_M | 4.81GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [LongWriter-glm4-9b-abliterated-Q2_K_L.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q2_K_L.gguf) | Q2_K_L | 4.60GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [LongWriter-glm4-9b-abliterated-Q3_K_S.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q3_K_S.gguf) | Q3_K_S | 4.59GB | false | Low quality, not recommended. |
| [LongWriter-glm4-9b-abliterated-IQ3_XS.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-IQ3_XS.gguf) | IQ3_XS | 4.43GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [LongWriter-glm4-9b-abliterated-Q2_K.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-Q2_K.gguf) | Q2_K | 3.99GB | false | Very low quality but surprisingly usable. |
| [LongWriter-glm4-9b-abliterated-IQ2_M.gguf](https://huggingface.co/bartowski/LongWriter-glm4-9b-abliterated-GGUF/blob/main/LongWriter-glm4-9b-abliterated-IQ2_M.gguf) | IQ2_M | 3.93GB | 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.
Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.
Thanks!
## Downloading using huggingface-cli
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/LongWriter-glm4-9b-abliterated-GGUF --include "LongWriter-glm4-9b-abliterated-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/LongWriter-glm4-9b-abliterated-GGUF --include "LongWriter-glm4-9b-abliterated-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (LongWriter-glm4-9b-abliterated-Q8_0) or download them all in place (./)
## Q4_0_X_X
These are *NOT* for Metal (Apple) offloading, only ARM chips.
If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
## Which file should I choose?
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.
## 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
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
+1
View File
@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}