初始化项目,由ModelHub XC社区提供模型

Model: bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC committed 2026-11-15 20:35:12 +08:00
commit bf3f5c0feb
31 files changed
+282

No files matched your search

+63
View File
@@ -0,0 +1,63 @@
*.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
Pantheon-RP-1.6.2-22b-Small-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small-f16.gguf filter=lfs diff=lfs merge=lfs -text
Pantheon-RP-1.6.2-22b-Small.imatrix filter=lfs diff=lfs merge=lfs -text
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4f59aeae6e2127dcbb95850ff93babfbddc4f6502d4250964acfc7dde298029c
size 7618966848
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fb74190597f246f5a1013048ed0fd2c9a03aabb53a7fea4977bb24dd8fee2426
size 7035434304
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7aabbfceeca05275337a7ea0ad45df6a0ed7d24e05cac5dd9d6344107f84f169
size 6646150464
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:449ab786436b73b3f1516350bf602409292f989d47d58c903d050ba0e2cd0b4c
size 5996557632
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3636edde14472ce181780a9d7fbe22ac07a6d4b61d1a1723cfd9a559a7cdca21
size 10062411072
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:717e489222b536e2325390d10b3b5b9f77a165c111b2fe0139efcf12a3f804b2
size 9176102208
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a76a2fe65aaa46c766d09ee58023c9dc615030a6e4b9cdfd0308186f6d5a5ea
size 11935298880
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:63819344a5bd8b2b700224719a1c5ea338b71f289ec666688e59e82b2818c460
size 8272098624
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c9431774c43aa0ce3b886fd25e7a39d359a34ac0b96c6bd12d13ac5a516bbd94
size 8468706624
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:961f3bb4da1b2650e335c20d26e9f1a860e041028c48779b50540c8495680a1d
size 11730433344
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fd62a7b64ad1d5dd299cc4bc5a54831adc416266f471f54657ab175f249797f0
size 10756830528
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4376262565cdfed606352faf325fb76b027be54a607602036797afb7a3401303
size 9641276736
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1564a578aebf2e49e9ecd1538a98a333688bfb6e1f86beef03085f57df092132
size 11906594112
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c99626248d175f2af976de6b2bce11d0780af52a797bb0a2356f962f4a31a9a3
size 12613203264
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3d9d46d850dac42ac0cb7d882fa0f0102b907b9735e6ebbfb0de51a40c79974f
size 12569163072
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dd1caa635c17c081210b189528c86431dd187d870dc6c9a00c3e226d1fe6488d
size 12569163072
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:036911815047db73acdc6d70007bbebacb95bb274d0eac54712bed0831de799c
size 12569163072
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6b731f68403834efabfd7487c0dbcdf7acda2883269e32b44aaa74423dd17208
size 13490664768
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e942f39361f4124405dafdeca2e5a3da34d539ed0d0043c368f440ea2d0cf38
size 13341242688
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:46156cfbb021f5a7193ffb300e75b9d9f2c9d963bdf2ff79b30084285958d76d
size 12660389184
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ec4858b03d2b358da544f2d617e97e2dbb6b769a6b5eff87c047e0dd99238d3d
size 15846815040
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bc65b0bbb48c45743231bdf20abc56ffbfbd8873a9587cabecc27a5ea7feb25e
size 15722558784
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac272ceb3f9fc1fa0b1a8fd174e1435a73dcd8da85a3b4da7f969485c5d85b25
size 15324820800
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5e10c87e482f71a494e88c76b0676987b079f3caf0b9a8ed8ef4ccad19296553
size 18252707136
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e50324d2b99f5aaf45769a98d39039b5ed17a45a74b6b50d4e0e9f3af80985be
size 18350224704
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1498088acd6ff3731fc2af386eb6bd3c5c24f9eff541945468062910e62190b2
size 23640552768
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ff537e3af72547f9b245c7c82d64c9a24a9b3627271d60123067560d87e898ef
size 44496729120
+3
View File
@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0d37c000be9a25484175d19b81bcb8ac6ed15330c32f90fa6b28622ad3cc114f
size 11940578
+134
View File
@@ -0,0 +1,134 @@
---
base_model: Gryphe/Pantheon-RP-1.6.2-22b-Small
language:
- en
license: other
license_name: mrl
license_link: https://mistral.ai/licenses/MRL-0.1.md
pipeline_tag: text-generation
tags:
- instruct
- finetune
- chatml
- axolotl
- roleplay
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of Pantheon-RP-1.6.2-22b-Small
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3901">b3901</a> for quantization.
Original model: https://huggingface.co/Gryphe/Pantheon-RP-1.6.2-22b-Small
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
```
<s>[INST] {prompt}[/INST]
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Pantheon-RP-1.6.2-22b-Small-f16.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-f16.gguf) | f16 | 44.50GB | false | Full F16 weights. |
| [Pantheon-RP-1.6.2-22b-Small-Q8_0.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q8_0.gguf) | Q8_0 | 23.64GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Pantheon-RP-1.6.2-22b-Small-Q6_K_L.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q6_K_L.gguf) | Q6_K_L | 18.35GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Pantheon-RP-1.6.2-22b-Small-Q6_K.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q6_K.gguf) | Q6_K | 18.25GB | false | Very high quality, near perfect, *recommended*. |
| [Pantheon-RP-1.6.2-22b-Small-Q5_K_L.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q5_K_L.gguf) | Q5_K_L | 15.85GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Pantheon-RP-1.6.2-22b-Small-Q5_K_M.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q5_K_M.gguf) | Q5_K_M | 15.72GB | false | High quality, *recommended*. |
| [Pantheon-RP-1.6.2-22b-Small-Q5_K_S.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q5_K_S.gguf) | Q5_K_S | 15.32GB | false | High quality, *recommended*. |
| [Pantheon-RP-1.6.2-22b-Small-Q4_K_L.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q4_K_L.gguf) | Q4_K_L | 13.49GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Pantheon-RP-1.6.2-22b-Small-Q4_K_M.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q4_K_M.gguf) | Q4_K_M | 13.34GB | false | Good quality, default size for must use cases, *recommended*. |
| [Pantheon-RP-1.6.2-22b-Small-Q4_K_S.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q4_K_S.gguf) | Q4_K_S | 12.66GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Pantheon-RP-1.6.2-22b-Small-Q4_0.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q4_0.gguf) | Q4_0 | 12.61GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Pantheon-RP-1.6.2-22b-Small-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q4_0_8_8.gguf) | Q4_0_8_8 | 12.57GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
| [Pantheon-RP-1.6.2-22b-Small-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q4_0_4_8.gguf) | Q4_0_4_8 | 12.57GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
| [Pantheon-RP-1.6.2-22b-Small-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q4_0_4_4.gguf) | Q4_0_4_4 | 12.57GB | 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*. |
| [Pantheon-RP-1.6.2-22b-Small-IQ4_XS.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-IQ4_XS.gguf) | IQ4_XS | 11.94GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Pantheon-RP-1.6.2-22b-Small-Q3_K_XL.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q3_K_XL.gguf) | Q3_K_XL | 11.91GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Pantheon-RP-1.6.2-22b-Small-Q3_K_L.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q3_K_L.gguf) | Q3_K_L | 11.73GB | false | Lower quality but usable, good for low RAM availability. |
| [Pantheon-RP-1.6.2-22b-Small-Q3_K_M.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q3_K_M.gguf) | Q3_K_M | 10.76GB | false | Low quality. |
| [Pantheon-RP-1.6.2-22b-Small-IQ3_M.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-IQ3_M.gguf) | IQ3_M | 10.06GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Pantheon-RP-1.6.2-22b-Small-Q3_K_S.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q3_K_S.gguf) | Q3_K_S | 9.64GB | false | Low quality, not recommended. |
| [Pantheon-RP-1.6.2-22b-Small-IQ3_XS.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-IQ3_XS.gguf) | IQ3_XS | 9.18GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Pantheon-RP-1.6.2-22b-Small-Q2_K_L.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q2_K_L.gguf) | Q2_K_L | 8.47GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Pantheon-RP-1.6.2-22b-Small-Q2_K.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-Q2_K.gguf) | Q2_K | 8.27GB | false | Very low quality but surprisingly usable. |
| [Pantheon-RP-1.6.2-22b-Small-IQ2_M.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-IQ2_M.gguf) | IQ2_M | 7.62GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
| [Pantheon-RP-1.6.2-22b-Small-IQ2_S.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-IQ2_S.gguf) | IQ2_S | 7.04GB | false | Low quality, uses SOTA techniques to be usable. |
| [Pantheon-RP-1.6.2-22b-Small-IQ2_XS.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-IQ2_XS.gguf) | IQ2_XS | 6.65GB | false | Low quality, uses SOTA techniques to be usable. |
| [Pantheon-RP-1.6.2-22b-Small-IQ2_XXS.gguf](https://huggingface.co/bartowski/Pantheon-RP-1.6.2-22b-Small-GGUF/blob/main/Pantheon-RP-1.6.2-22b-Small-IQ2_XXS.gguf) | IQ2_XXS | 6.00GB | false | Very low quality, uses SOTA techniques to be 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/Pantheon-RP-1.6.2-22b-Small-GGUF --include "Pantheon-RP-1.6.2-22b-Small-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/Pantheon-RP-1.6.2-22b-Small-GGUF --include "Pantheon-RP-1.6.2-22b-Small-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Pantheon-RP-1.6.2-22b-Small-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}