初始化项目，由ModelHub XC社区提供模型
Model: bartowski/NousResearch_Hermes-4-14B-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
47
.gitattributes
vendored
Normal file
47
.gitattributes
vendored
Normal file
@@ -0,0 +1,47 @@
|
|||||||
|
*.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
|
||||||
3
NousResearch_Hermes-4-14B-IQ2_M.gguf
Normal file
3
NousResearch_Hermes-4-14B-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:606b7aae87a194dabd0ad756eb75a9f4fa8abe23f1307cac12cc709a1da05f8a
|
||||||
|
size 5322941376
|
||||||
3
NousResearch_Hermes-4-14B-IQ2_S.gguf
Normal file
3
NousResearch_Hermes-4-14B-IQ2_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:24fae4ceebd0dd5a71e7085cf9f55bba51790dc4b9fe3ed5cd0f7d5f681d8d9f
|
||||||
|
size 4963312576
|
||||||
3
NousResearch_Hermes-4-14B-IQ2_XS.gguf
Normal file
3
NousResearch_Hermes-4-14B-IQ2_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:23e133194bc474eaad0995b23c35ae3be5ae7b9c6ff04583ea4e5f0067f92b93
|
||||||
|
size 4691589056
|
||||||
3
NousResearch_Hermes-4-14B-IQ3_M.gguf
Normal file
3
NousResearch_Hermes-4-14B-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f30dec8430bedae8239fc735799172cb3709a598c71ea630f070d67b5ceef478
|
||||||
|
size 6883409856
|
||||||
3
NousResearch_Hermes-4-14B-IQ3_XS.gguf
Normal file
3
NousResearch_Hermes-4-14B-IQ3_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b1c65133875488ca08a77ab9f996780700c5dfa4e404bdd25836707170d625b8
|
||||||
|
size 6375301056
|
||||||
3
NousResearch_Hermes-4-14B-IQ3_XXS.gguf
Normal file
3
NousResearch_Hermes-4-14B-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0e47a1839617e50c4caf62d51eb935c66ba0de6795e7f4c5d92dd89c345afc03
|
||||||
|
size 5942666176
|
||||||
3
NousResearch_Hermes-4-14B-IQ4_NL.gguf
Normal file
3
NousResearch_Hermes-4-14B-IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9ef512279cd6937d8f29540718a22ddd59fd1e94d8192538640ae65fa73c1b08
|
||||||
|
size 8541363136
|
||||||
3
NousResearch_Hermes-4-14B-IQ4_XS.gguf
Normal file
3
NousResearch_Hermes-4-14B-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d76605ab41b4a0bbd216eca465e3f286b740a1dce7222e8dd041e06e97169c0d
|
||||||
|
size 8110730176
|
||||||
3
NousResearch_Hermes-4-14B-Q2_K.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:abc45511090b41bc7e343918be7415f1075f76786893a1f55a60f1a71b8c9efb
|
||||||
|
size 5753983936
|
||||||
3
NousResearch_Hermes-4-14B-Q2_K_L.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q2_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:982891e3cd50b9f04bef03c5c0bef86fee8e8873160423ed1882304d14bd2146
|
||||||
|
size 6513663936
|
||||||
3
NousResearch_Hermes-4-14B-Q3_K_L.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:aaf50b3f1ae23fac8a3724c038644eba2bb1312c2bb9796c24cbd11dca759493
|
||||||
|
size 7900651456
|
||||||
3
NousResearch_Hermes-4-14B-Q3_K_M.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2f1c5ba4404a4de253c256f59142bf97b8c21846fe8c58611e6eabf3730bf1a7
|
||||||
|
size 7321313216
|
||||||
3
NousResearch_Hermes-4-14B-Q3_K_S.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:074cdd0e242a2e9132021b0154573b7e53fc24ce72d399c3823a5eef670c2718
|
||||||
|
size 6657105856
|
||||||
3
NousResearch_Hermes-4-14B-Q3_K_XL.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q3_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:13584188db5df8cd7ada44110b0f8b0b35c47f3d4dc8500f96c6a8b68efb2104
|
||||||
|
size 8581324736
|
||||||
3
NousResearch_Hermes-4-14B-Q4_0.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f6351870abf09a9b00609a36cba214345fbe20df24dde64582899b504a50c47c
|
||||||
|
size 8543001536
|
||||||
3
NousResearch_Hermes-4-14B-Q4_1.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:0e2accf2f2275c431086cf1a848d8dd90172e297ffeaee3fb7e73dffac674ec1
|
||||||
|
size 9389521856
|
||||||
3
NousResearch_Hermes-4-14B-Q4_K_L.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q4_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8c4d4a2c4776ef48e606f441ed34db1b36408fd8d6335ed943a7d6f12b4bc4ca
|
||||||
|
size 9579110336
|
||||||
3
NousResearch_Hermes-4-14B-Q4_K_M.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7ad9be1e446e3da0c149fdf55284c90be666d3e13c6e2581587853f4f9538073
|
||||||
|
size 9001753536
|
||||||
3
NousResearch_Hermes-4-14B-Q4_K_S.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d79292d45903c878ef03d6eef649b8b664fbd0dce058acd2ed99aa6438726869
|
||||||
|
size 8573475776
|
||||||
3
NousResearch_Hermes-4-14B-Q5_K_L.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q5_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:faa7e2ad0ad51ab6e148ff68be0eba729cc94a0b2a0dc965f37975c605a3c1b5
|
||||||
|
size 10994687936
|
||||||
3
NousResearch_Hermes-4-14B-Q5_K_M.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:aebc57a6319d0486a5adb0c6891d51f383ea5c29281d764a87085b474a4af06b
|
||||||
|
size 10514570176
|
||||||
3
NousResearch_Hermes-4-14B-Q5_K_S.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:157559d9ca65c4056514b0950f79a405d325b53e4c7bc7918a168c45ea60815e
|
||||||
|
size 10263894976
|
||||||
3
NousResearch_Hermes-4-14B-Q6_K.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f7156c9ad8e9a0a4e01792714edb81424882507f7929a4d00f25689ccdb29552
|
||||||
|
size 12121937856
|
||||||
3
NousResearch_Hermes-4-14B-Q6_K_L.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q6_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:290026a86834b54ea6a9945ed04889e7b8039a08bc025973ea408c7ce0740d59
|
||||||
|
size 12498739136
|
||||||
3
NousResearch_Hermes-4-14B-Q8_0.gguf
Normal file
3
NousResearch_Hermes-4-14B-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:96ce4ecbe5906316b9b71ff6c69575a952e661366b97e615e6a02f449b28cfcd
|
||||||
|
size 15698534336
|
||||||
3
NousResearch_Hermes-4-14B-bf16.gguf
Normal file
3
NousResearch_Hermes-4-14B-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6bdf70e6a7115e5999fbbe02a21d0ce73243a7d44b19b13e5393e6c74dc99482
|
||||||
|
size 29543423648
|
||||||
3
NousResearch_Hermes-4-14B-imatrix.gguf
Normal file
3
NousResearch_Hermes-4-14B-imatrix.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:155021128cfb549d9d409991c852649a88dd8ac5d42d0badfb176913e09c21c2
|
||||||
|
size 7743584
|
||||||
166
README.md
Normal file
166
README.md
Normal file
@@ -0,0 +1,166 @@
|
|||||||
|
---
|
||||||
|
quantized_by: bartowski
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
base_model: NousResearch/Hermes-4-14B
|
||||||
|
base_model_relation: quantized
|
||||||
|
---
|
||||||
|
|
||||||
|
## Llamacpp imatrix Quantizations of Hermes-4-14B by NousResearch
|
||||||
|
|
||||||
|
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/b6317">b6317</a> for quantization.
|
||||||
|
|
||||||
|
Original model: https://huggingface.co/NousResearch/Hermes-4-14B
|
||||||
|
|
||||||
|
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 |
|
||||||
|
| -------- | ---------- | --------- | ----- | ----------- |
|
||||||
|
| [Hermes-4-14B-bf16.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-bf16.gguf) | bf16 | 29.54GB | false | Full BF16 weights. |
|
||||||
|
| [Hermes-4-14B-Q8_0.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q8_0.gguf) | Q8_0 | 15.70GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||||
|
| [Hermes-4-14B-Q6_K_L.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q6_K_L.gguf) | Q6_K_L | 12.50GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||||
|
| [Hermes-4-14B-Q6_K.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q6_K.gguf) | Q6_K | 12.12GB | false | Very high quality, near perfect, *recommended*. |
|
||||||
|
| [Hermes-4-14B-Q5_K_L.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q5_K_L.gguf) | Q5_K_L | 10.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||||
|
| [Hermes-4-14B-Q5_K_M.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q5_K_M.gguf) | Q5_K_M | 10.51GB | false | High quality, *recommended*. |
|
||||||
|
| [Hermes-4-14B-Q5_K_S.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q5_K_S.gguf) | Q5_K_S | 10.26GB | false | High quality, *recommended*. |
|
||||||
|
| [Hermes-4-14B-Q4_K_L.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q4_K_L.gguf) | Q4_K_L | 9.58GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||||
|
| [Hermes-4-14B-Q4_1.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q4_1.gguf) | Q4_1 | 9.39GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||||
|
| [Hermes-4-14B-Q4_K_M.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q4_K_M.gguf) | Q4_K_M | 9.00GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||||
|
| [Hermes-4-14B-Q3_K_XL.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q3_K_XL.gguf) | Q3_K_XL | 8.58GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
|
||||||
|
| [Hermes-4-14B-Q4_K_S.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q4_K_S.gguf) | Q4_K_S | 8.57GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||||
|
| [Hermes-4-14B-Q4_0.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q4_0.gguf) | Q4_0 | 8.54GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||||
|
| [Hermes-4-14B-IQ4_NL.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-IQ4_NL.gguf) | IQ4_NL | 8.54GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||||
|
| [Hermes-4-14B-IQ4_XS.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-IQ4_XS.gguf) | IQ4_XS | 8.11GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||||
|
| [Hermes-4-14B-Q3_K_L.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q3_K_L.gguf) | Q3_K_L | 7.90GB | false | Lower quality but usable, good for low RAM availability. |
|
||||||
|
| [Hermes-4-14B-Q3_K_M.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q3_K_M.gguf) | Q3_K_M | 7.32GB | false | Low quality. |
|
||||||
|
| [Hermes-4-14B-IQ3_M.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-IQ3_M.gguf) | IQ3_M | 6.88GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||||
|
| [Hermes-4-14B-Q3_K_S.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q3_K_S.gguf) | Q3_K_S | 6.66GB | false | Low quality, not recommended. |
|
||||||
|
| [Hermes-4-14B-Q2_K_L.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q2_K_L.gguf) | Q2_K_L | 6.51GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||||
|
| [Hermes-4-14B-IQ3_XS.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-IQ3_XS.gguf) | IQ3_XS | 6.38GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||||
|
| [Hermes-4-14B-IQ3_XXS.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-IQ3_XXS.gguf) | IQ3_XXS | 5.94GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||||
|
| [Hermes-4-14B-Q2_K.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-Q2_K.gguf) | Q2_K | 5.75GB | false | Very low quality but surprisingly usable. |
|
||||||
|
| [Hermes-4-14B-IQ2_M.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-IQ2_M.gguf) | IQ2_M | 5.32GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
|
||||||
|
| [Hermes-4-14B-IQ2_S.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-IQ2_S.gguf) | IQ2_S | 4.96GB | false | Low quality, uses SOTA techniques to be usable. |
|
||||||
|
| [Hermes-4-14B-IQ2_XS.gguf](https://huggingface.co/bartowski/NousResearch_Hermes-4-14B-GGUF/blob/main/NousResearch_Hermes-4-14B-IQ2_XS.gguf) | IQ2_XS | 4.69GB | false | 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.
|
||||||
|
|
||||||
|
## 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/NousResearch_Hermes-4-14B-GGUF --include "NousResearch_Hermes-4-14B-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/NousResearch_Hermes-4-14B-GGUF --include "NousResearch_Hermes-4-14B-Q8_0/*" --local-dir ./
|
||||||
|
```
|
||||||
|
|
||||||
|
You can either specify a new local-dir (NousResearch_Hermes-4-14B-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}
|
||||||
Reference in New Issue
Block a user