bartowski/PokeeAI_pokee_research_7b-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/PokeeAI_pokee_research_7b-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-11 15:37:13 +08:00
commit 00c6f3cfee
28 changed files with 321 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
.gitattributes vendored Normal file
View File

@@ -0,0 +1,73 @@
*.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
*.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
PokeeAI_pokee_research_7b-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-bf16.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
PokeeAI_pokee_research_7b-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text

3
PokeeAI_pokee_research_7b-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:28fa10ae4eb8daed6074a65eb7fa0161e41f2768dd7bda2235dff66785a9137a
size 2780343072

3
PokeeAI_pokee_research_7b-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9201566ca76ec516f9e37eb56f5db008fbe33dde20cec69bcb4cc0881e95a48f
size 3574012704

3
PokeeAI_pokee_research_7b-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:77c4a65f9bb728cbdf8b4f7ff93d3c9489e52074a11263ac9774ebf5c8c4af9d
size 3346256672

3
PokeeAI_pokee_research_7b-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b170bd31ae3cb6b917e20ccae012d92109bae6e31dd9988e8dc44688192919d8
size 3114515232

3
PokeeAI_pokee_research_7b-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:60a1381fcd40d246dbd25a51e80d6d7865274953057a61a82ec565173205963a
size 4437814048

3
PokeeAI_pokee_research_7b-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef196536118ef41c6ad680bd202d8926e98b7657c6616d0237eed97527565b4d
size 4218473248

3
PokeeAI_pokee_research_7b-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:832b9f19b76962468fa34cb672248088a2f8b2f21836d8690d7930f288ca1949
size 3015940896

3
PokeeAI_pokee_research_7b-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d57c5a51491c636c5db2d7b29898f06d0925da21399efdb081bc59b084f74997
size 3548164896

3
PokeeAI_pokee_research_7b-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9f8f0ba9feebac6715296dc1e5f279b233aee1a0630c643632743b3d956d8db2
size 4088460064

3
PokeeAI_pokee_research_7b-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b837c33d20decac8a8fe39eec26ab36c75fafce639dab4bafcd0b53ea9f630b9
size 3808391968

3
PokeeAI_pokee_research_7b-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9faddb0b833de8da9e3e3a73e0fcb9eb6be705f67ea3d03969ad0eab756f59f7
size 3492369184

3
PokeeAI_pokee_research_7b-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ad54d39a08dba49c6d780b44cf3cd3a56bb0e3d2c82b295e0452222fb8fd6436
size 4565332768

3
PokeeAI_pokee_research_7b-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:92e62e4f3beadfd8cda0cbf055d43e9907061d147f721f4e4d125d42caa675b2
size 4444121888

3
PokeeAI_pokee_research_7b-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cfb86cbfb4915900d247bb32e1e4b0dbd39383aa2245d22dbc8ba48dbc55146c
size 4873284384

3
PokeeAI_pokee_research_7b-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4424229a6ee678d8a9ae1262899eb554cfa1cd32c20dabeb9163f34ef8801129
size 5087564576

3
PokeeAI_pokee_research_7b-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f16c5c3aaa5e01e897431e4b6dfa15d7fcb69bcd71050716606ccb13eb5eb9c6
size 4683074336

3
PokeeAI_pokee_research_7b-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f3d2675a077d2f97c8585111119047d08a7e86563b67e2836ce6907eba79e3b4
size 4457769760

3
PokeeAI_pokee_research_7b-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c6b54963e3120426af0ca78cb8deb5b0cdc497f0b92898aad09e029268ad9d7d
size 5781197600

3
PokeeAI_pokee_research_7b-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:504b6d8d349b640d5721e50eb7ccd070a2647218eef07a7db8d0f548f382b64e
size 5444832032

3
PokeeAI_pokee_research_7b-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9395de19603e0eec5f42912c35e9c61fbbcab139a78af31989d5c9352a902df2
size 5315177248

3
PokeeAI_pokee_research_7b-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e4ebc622c63e6d913fa6a4b74fb897134d59cbd09d38bdbe6e0322360444200
size 6254199584

3
PokeeAI_pokee_research_7b-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ab4ca180a75d718abd472c234f995f2d92d3a2e226169e8252872576a7707e18
size 6518182688

3
PokeeAI_pokee_research_7b-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5a2225795965d37810b95ac57f58f33920a23b7ce0171030fc15ae6c247d212e
size 8098525984

3
PokeeAI_pokee_research_7b-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:23cfccba9f570f4b590dfae298399a8787bf66544ddee7b639f08b1d09365d95
size 15237853696

3
PokeeAI_pokee_research_7b-imatrix.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:516829bf25b33c8dc9e47dddadb5de10cb52527dcc3dfccd6dfee48754496639
size 4560352

172
README.md Normal file
View File

@@ -0,0 +1,172 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model_relation: quantized
base_model: PokeeAI/pokee_research_7b
---
## Llamacpp imatrix Quantizations of pokee_research_7b by PokeeAI
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/b6818">b6818</a> for quantization.
Original model: https://huggingface.co/PokeeAI/pokee_research_7b
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 chat template specified so default is used. This may be incorrect, check original model card for details.
```
<|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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [pokee_research_7b-bf16.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-bf16.gguf) | bf16 | 15.24GB | false | Full BF16 weights. |
| [pokee_research_7b-Q8_0.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q8_0.gguf) | Q8_0 | 8.10GB | false | Extremely high quality, generally unneeded but max available quant. |
| [pokee_research_7b-Q6_K_L.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q6_K_L.gguf) | Q6_K_L | 6.52GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [pokee_research_7b-Q6_K.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q6_K.gguf) | Q6_K | 6.25GB | false | Very high quality, near perfect, *recommended*. |
| [pokee_research_7b-Q5_K_L.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q5_K_L.gguf) | Q5_K_L | 5.78GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [pokee_research_7b-Q5_K_M.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q5_K_M.gguf) | Q5_K_M | 5.44GB | false | High quality, *recommended*. |
| [pokee_research_7b-Q5_K_S.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q5_K_S.gguf) | Q5_K_S | 5.32GB | false | High quality, *recommended*. |
| [pokee_research_7b-Q4_K_L.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q4_K_L.gguf) | Q4_K_L | 5.09GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [pokee_research_7b-Q4_1.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q4_1.gguf) | Q4_1 | 4.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [pokee_research_7b-Q4_K_M.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. |
| [pokee_research_7b-Q3_K_XL.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q3_K_XL.gguf) | Q3_K_XL | 4.57GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [pokee_research_7b-Q4_K_S.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q4_K_S.gguf) | Q4_K_S | 4.46GB | false | Slightly lower quality with more space savings, *recommended*. |
| [pokee_research_7b-Q4_0.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q4_0.gguf) | Q4_0 | 4.44GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [pokee_research_7b-IQ4_NL.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ4_NL.gguf) | IQ4_NL | 4.44GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [pokee_research_7b-IQ4_XS.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ4_XS.gguf) | IQ4_XS | 4.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [pokee_research_7b-Q3_K_L.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. |
| [pokee_research_7b-Q3_K_M.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q3_K_M.gguf) | Q3_K_M | 3.81GB | false | Low quality. |
| [pokee_research_7b-IQ3_M.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ3_M.gguf) | IQ3_M | 3.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [pokee_research_7b-Q2_K_L.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q2_K_L.gguf) | Q2_K_L | 3.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [pokee_research_7b-Q3_K_S.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q3_K_S.gguf) | Q3_K_S | 3.49GB | false | Low quality, not recommended. |
| [pokee_research_7b-IQ3_XS.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ3_XS.gguf) | IQ3_XS | 3.35GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [pokee_research_7b-IQ3_XXS.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ3_XXS.gguf) | IQ3_XXS | 3.11GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [pokee_research_7b-Q2_K.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q2_K.gguf) | Q2_K | 3.02GB | false | Very low quality but surprisingly usable. |
| [pokee_research_7b-IQ2_M.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ2_M.gguf) | IQ2_M | 2.78GB | 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/PokeeAI_pokee_research_7b-GGUF --include "PokeeAI_pokee_research_7b-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/PokeeAI_pokee_research_7b-GGUF --include "PokeeAI_pokee_research_7b-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (PokeeAI_pokee_research_7b-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
View File

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