bartowski/Falcon3-10B-Base-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/Falcon3-10B-Base-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-10 05:56:13 +08:00
commit fceb51e931
27 changed files with 397 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
.gitattributes vendored Normal file
View File

@@ -0,0 +1,59 @@
*.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
Falcon3-10B-Base-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base-f16.gguf filter=lfs diff=lfs merge=lfs -text
Falcon3-10B-Base.imatrix filter=lfs diff=lfs merge=lfs -text

3
Falcon3-10B-Base-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:90f97645c2b2bd71ab0b1f96ea66f31a8ea2da94d0c70531f45469697985a53b
size 3592343136

3
Falcon3-10B-Base-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4789435a6bf197010121874cf58588e153afa2b3a0b95288e090f5bf267cb9d6
size 4704984672

3
Falcon3-10B-Base-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0af7cd74ba67bc94e231c326c70282e22f261e7185bcffc220ff7a6f4a542dce
size 4368477792

3
Falcon3-10B-Base-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:88eed683ccfc3eb67dd3c89ae0f2e9169d324287c0eef5d8c2734678d4c8a740
size 5906345568

3
Falcon3-10B-Base-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e4cc8e5cd2720c14e971285df4da544ebe0279444dac56e4de15115debfc2f41
size 5596884576

3
Falcon3-10B-Base-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d17b7c586f31d51e8e8bab5ea751385346bdce5671e675e9185bffc933f0fe6d
size 3924045408

3
Falcon3-10B-Base-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a03ebedf9588469204367d216247292189e190dbd9db4479ee8d2fc814305b87
size 4317261408

3
Falcon3-10B-Base-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0acddb4584d4305bdd701dbff2d2130c2fce0ad019cc1abc658f1e567cab6bf5
size 5450804832

3
Falcon3-10B-Base-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e992031085ecb43fbfb4a928cfbc5839a42879891718612b40685b5b046121c1
size 5052477024

3
Falcon3-10B-Base-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:029cdded6091515826ce01ab9aaf5034c1bf3c76e926d739e81b5df6a77fc83a
size 4591136352

3
Falcon3-10B-Base-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5951f6679aa305ba5a2bd3ff321052a075f408ba972fd7c4c86dc8d424aa6e93
size 5803126368

3
Falcon3-10B-Base-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5e6adcea45adbb0dd925a23a694e2be75092dbe090ccdb0398abac8bf65270c5
size 5928463968

3
Falcon3-10B-Base-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ced03a5058cdf6788274b8066dc57420c5f888bd2441dfb640a35a71f9c04df5
size 6525267552

3
Falcon3-10B-Base-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eadbbe62c94588423e1bbfe0dbd023b31b1066c225ba90e8dc309be9c6b1cbde
size 6586363488

3
Falcon3-10B-Base-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5aec73856889bbdaa734f4d6d1855f5e8901ab9d7f3e8842ad29abe203822c79
size 6287519328

3
Falcon3-10B-Base-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:177aec9f4e50f312d78c9e99b4d734d17a4e312ec3546e55dca3e728d8da1b4f
size 5952155232

3
Falcon3-10B-Base-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0013c344b8a808dd67a7b79218d1390594d1a9a6eefa83e71200740db254de74
size 7589064288

3
Falcon3-10B-Base-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de10a2e9fe347116f2cbde3559afea5e6de83e7d8aed5fd692d0103ea05b332b
size 7340551776

3
Falcon3-10B-Base-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e34548e39c9dc9a62adc72b7675a2d11e82e49e497e5d28cd2a7837b1300a914
size 7144189536

3
Falcon3-10B-Base-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3d675080233b291b8edd303f9893ac1822b4f625f5855771f19bf2fee25556c1
size 8459398752

3
Falcon3-10B-Base-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a1da88e86e459f025e3108e9f9e03fd655f4b6caf1dca0409e78550e3bcbd577
size 8654433888

3
Falcon3-10B-Base-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5e1c0145782b23f8445baed5ccfc0960d238a1f474c1a5d312135cb241f2ab79
size 10955239008

3
Falcon3-10B-Base-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:131310fa63819e7b26d2b7afce3d2e45985cd090ee8467b7efd0eda84fe51815
size 20616555872

3
Falcon3-10B-Base.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d9addc41581aab5f9155d00ca6c3f1d145c8c392ba039e63912da0f1b7ec3edb
size 6644818

265
README.md Normal file
View File

@@ -0,0 +1,265 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
license_name: falcon-llm-license
language:
- en
- fr
- es
- pt
license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
base_model: tiiuae/Falcon3-10B-Base
license: other
tags:
- falcon3
model-index:
- name: Falcon3-10B-Base
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 36.48
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Base
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 41.38
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Base
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 24.77
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Base
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 12.75
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Base
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 14.17
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Base
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 36.0
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Base
name: Open LLM Leaderboard
---
## Llamacpp imatrix Quantizations of Falcon3-10B-Base
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4381">b4381</a> for quantization.
Original model: https://huggingface.co/tiiuae/Falcon3-10B-Base
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
No prompt format found, check original model page
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Falcon3-10B-Base-f16.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-f16.gguf) | f16 | 20.62GB | false | Full F16 weights. |
| [Falcon3-10B-Base-Q8_0.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q8_0.gguf) | Q8_0 | 10.96GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Falcon3-10B-Base-Q6_K_L.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q6_K_L.gguf) | Q6_K_L | 8.65GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Falcon3-10B-Base-Q6_K.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q6_K.gguf) | Q6_K | 8.46GB | false | Very high quality, near perfect, *recommended*. |
| [Falcon3-10B-Base-Q5_K_L.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q5_K_L.gguf) | Q5_K_L | 7.59GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Falcon3-10B-Base-Q5_K_M.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q5_K_M.gguf) | Q5_K_M | 7.34GB | false | High quality, *recommended*. |
| [Falcon3-10B-Base-Q5_K_S.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q5_K_S.gguf) | Q5_K_S | 7.14GB | false | High quality, *recommended*. |
| [Falcon3-10B-Base-Q4_K_L.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q4_K_L.gguf) | Q4_K_L | 6.59GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Falcon3-10B-Base-Q4_1.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q4_1.gguf) | Q4_1 | 6.53GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Falcon3-10B-Base-Q4_K_M.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q4_K_M.gguf) | Q4_K_M | 6.29GB | false | Good quality, default size for most use cases, *recommended*. |
| [Falcon3-10B-Base-Q4_K_S.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q4_K_S.gguf) | Q4_K_S | 5.95GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Falcon3-10B-Base-Q4_0.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q4_0.gguf) | Q4_0 | 5.93GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Falcon3-10B-Base-IQ4_NL.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-IQ4_NL.gguf) | IQ4_NL | 5.91GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Falcon3-10B-Base-Q3_K_XL.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q3_K_XL.gguf) | Q3_K_XL | 5.80GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Falcon3-10B-Base-IQ4_XS.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-IQ4_XS.gguf) | IQ4_XS | 5.60GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Falcon3-10B-Base-Q3_K_L.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q3_K_L.gguf) | Q3_K_L | 5.45GB | false | Lower quality but usable, good for low RAM availability. |
| [Falcon3-10B-Base-Q3_K_M.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q3_K_M.gguf) | Q3_K_M | 5.05GB | false | Low quality. |
| [Falcon3-10B-Base-IQ3_M.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-IQ3_M.gguf) | IQ3_M | 4.70GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Falcon3-10B-Base-Q3_K_S.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q3_K_S.gguf) | Q3_K_S | 4.59GB | false | Low quality, not recommended. |
| [Falcon3-10B-Base-IQ3_XS.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-IQ3_XS.gguf) | IQ3_XS | 4.37GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Falcon3-10B-Base-Q2_K_L.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q2_K_L.gguf) | Q2_K_L | 4.32GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Falcon3-10B-Base-Q2_K.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-Q2_K.gguf) | Q2_K | 3.92GB | false | Very low quality but surprisingly usable. |
| [Falcon3-10B-Base-IQ2_M.gguf](https://huggingface.co/bartowski/Falcon3-10B-Base-GGUF/blob/main/Falcon3-10B-Base-IQ2_M.gguf) | IQ2_M | 3.59GB | 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/Falcon3-10B-Base-GGUF --include "Falcon3-10B-Base-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/Falcon3-10B-Base-GGUF --include "Falcon3-10B-Base-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Falcon3-10B-Base-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 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.
</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.
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}