bartowski/LiquidAI_LFM2-1.2B-Extract-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/LiquidAI_LFM2-1.2B-Extract-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-25 14:56:12 +08:00
commit fafe19aad9
28 changed files with 307 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

70
.gitattributes vendored Normal file
View File

@@ -0,0 +1,70 @@
*.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
LiquidAI_LFM2-1.2B-Extract-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
LiquidAI_LFM2-1.2B-Extract-bf16.gguf filter=lfs diff=lfs merge=lfs -text

3
LiquidAI_LFM2-1.2B-Extract-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c008e0b877d13fbf2db1d483335e242b6ccc14face080d57169af14b4c6c228e
size 434131520

3
LiquidAI_LFM2-1.2B-Extract-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:20996c95a8630101d9bfc6ce3480327006be06216bc2ec96676392c5b3ff091f
size 566792768

3
LiquidAI_LFM2-1.2B-Extract-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7867596f613618563d50a4d18593bae596412cfbbe1be4bd0a4bb6cbb85c464a
size 537809472

3
LiquidAI_LFM2-1.2B-Extract-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f562f8c3b934201723a1acc7eb60fc2a9b8c16c507798211ad25b285366e651b
size 490984000

3
LiquidAI_LFM2-1.2B-Extract-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a09e13b8e79109564d1ed7e91454cc8bf8e2f9154a8018a004df2faa8367eca0
size 695751232

3
LiquidAI_LFM2-1.2B-Extract-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e51de9be31efdea88f19991e76883ba7fb240dd3fa0704f2aa288415d59eee14
size 663376448

3
LiquidAI_LFM2-1.2B-Extract-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:155415705db60818e09139435222b30f072ac122f9d6949a76366ad5d947a57c
size 483398208

3
LiquidAI_LFM2-1.2B-Extract-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bdce0f4c51202132ab4751f20ea3e4a1d34023d82b8d6a721b1f3df74c39aea2
size 515904064

3
LiquidAI_LFM2-1.2B-Extract-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8a694b9a8073e7aeede29550dd08ce59179e870c91736db8548d8bee860cef1d
size 635474496

3
LiquidAI_LFM2-1.2B-Extract-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9affb8c4fce6eaa9402c0b3bc3bd028b28c92212317b02dc706b23203ef2698c
size 600347200

3
LiquidAI_LFM2-1.2B-Extract-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:91e0cf8c93d904dc0bc06f8e6a58a8ae269709785bbfe4911644b0930e5a36ee
size 558158400

3
LiquidAI_LFM2-1.2B-Extract-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:531d2d752c778559fbea9e70715beab337e0570b7c729bfa313d294f88ed2388
size 667980352

3
LiquidAI_LFM2-1.2B-Extract-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1be66107278e2d07290777beda3d48f59a3244f1c4b9b4636c94589d98f4557e
size 697848384

3
LiquidAI_LFM2-1.2B-Extract-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f2d74bc9a7584f60e0ceb6527749327496ff55931c680f98bc2825fd24b6a4af
size 760500800

3
LiquidAI_LFM2-1.2B-Extract-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aed757aa25c0c4b78b9cc30686eeef2d694b9da5b62a6663c756c65ceb0adb15
size 763400768

3
LiquidAI_LFM2-1.2B-Extract-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97a1c5600045e9ade49bc4a9e3df083cef7c82b05a6d47ea2e58ab44cc98b16a
size 730894912

3
LiquidAI_LFM2-1.2B-Extract-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b5ec71f850948fc3f68ab4475a8ed6d334cdf3bf327a3c4eca116392883a104
size 700469824

3
LiquidAI_LFM2-1.2B-Extract-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8e54d9af3b7ec44e3d34e50774006f68b53792f3cbb61195c181fbedfe230112
size 875860544

3
LiquidAI_LFM2-1.2B-Extract-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:78b1a2727916a07f56de63697cbf912881c6f850c2ead23350870f1daa16f960
size 843354688

3
LiquidAI_LFM2-1.2B-Extract-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c552ac9ce7849fed1407ea08188bd691c0dd2035800fa14bd5f0fd35c02cca5b
size 825250368

3
LiquidAI_LFM2-1.2B-Extract-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a3467b1f66e174a050fa2af856e3eb57696dfa8ed96076fdc76ab71fd47abbb0
size 962843200

3
LiquidAI_LFM2-1.2B-Extract-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6498023e408ccbfa349f35dc7f2d728d4b3b8a4351fb304cfb25125f6ffb1ebc
size 995349056

3
LiquidAI_LFM2-1.2B-Extract-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5e3a583bab4bb92e02a7944abe1aadd369e07a7349e33e372952aacced7e11b9
size 1246253632

3
LiquidAI_LFM2-1.2B-Extract-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:218a8147b6de57b76ff1ef6e530e522e1001b43375edb975defc8e0b58ddb24c
size 2343325984

BIN
LiquidAI_LFM2-1.2B-Extract-imatrix.gguf Normal file
View File

Binary file not shown.

164
README.md Normal file
View File

@@ -0,0 +1,164 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model_relation: quantized
base_model: LiquidAI/LFM2-1.2B-Extract
---
## Llamacpp imatrix Quantizations of LFM2-1.2B-Extract by LiquidAI
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/b6683">b6683</a> for quantization.
Original model: https://huggingface.co/LiquidAI/LFM2-1.2B-Extract
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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [LFM2-1.2B-Extract-bf16.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-bf16.gguf) | bf16 | 2.34GB | false | Full BF16 weights. |
| [LFM2-1.2B-Extract-Q8_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q8_0.gguf) | Q8_0 | 1.25GB | false | Extremely high quality, generally unneeded but max available quant. |
| [LFM2-1.2B-Extract-Q6_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q6_K_L.gguf) | Q6_K_L | 1.00GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [LFM2-1.2B-Extract-Q6_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q6_K.gguf) | Q6_K | 0.96GB | false | Very high quality, near perfect, *recommended*. |
| [LFM2-1.2B-Extract-Q5_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q5_K_L.gguf) | Q5_K_L | 0.88GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [LFM2-1.2B-Extract-Q5_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q5_K_M.gguf) | Q5_K_M | 0.84GB | false | High quality, *recommended*. |
| [LFM2-1.2B-Extract-Q5_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q5_K_S.gguf) | Q5_K_S | 0.83GB | false | High quality, *recommended*. |
| [LFM2-1.2B-Extract-Q4_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q4_K_L.gguf) | Q4_K_L | 0.76GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [LFM2-1.2B-Extract-Q4_1.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q4_1.gguf) | Q4_1 | 0.76GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [LFM2-1.2B-Extract-Q4_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q4_K_M.gguf) | Q4_K_M | 0.73GB | false | Good quality, default size for most use cases, *recommended*. |
| [LFM2-1.2B-Extract-Q4_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q4_K_S.gguf) | Q4_K_S | 0.70GB | false | Slightly lower quality with more space savings, *recommended*. |
| [LFM2-1.2B-Extract-Q4_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q4_0.gguf) | Q4_0 | 0.70GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [LFM2-1.2B-Extract-IQ4_NL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ4_NL.gguf) | IQ4_NL | 0.70GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [LFM2-1.2B-Extract-Q3_K_XL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q3_K_XL.gguf) | Q3_K_XL | 0.67GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [LFM2-1.2B-Extract-IQ4_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ4_XS.gguf) | IQ4_XS | 0.66GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [LFM2-1.2B-Extract-Q3_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q3_K_L.gguf) | Q3_K_L | 0.64GB | false | Lower quality but usable, good for low RAM availability. |
| [LFM2-1.2B-Extract-Q3_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q3_K_M.gguf) | Q3_K_M | 0.60GB | false | Low quality. |
| [LFM2-1.2B-Extract-IQ3_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ3_M.gguf) | IQ3_M | 0.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [LFM2-1.2B-Extract-Q3_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q3_K_S.gguf) | Q3_K_S | 0.56GB | false | Low quality, not recommended. |
| [LFM2-1.2B-Extract-IQ3_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ3_XS.gguf) | IQ3_XS | 0.54GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [LFM2-1.2B-Extract-Q2_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q2_K_L.gguf) | Q2_K_L | 0.52GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [LFM2-1.2B-Extract-IQ3_XXS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ3_XXS.gguf) | IQ3_XXS | 0.49GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [LFM2-1.2B-Extract-Q2_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-Q2_K.gguf) | Q2_K | 0.48GB | false | Very low quality but surprisingly usable. |
| [LFM2-1.2B-Extract-IQ2_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2-1.2B-Extract-GGUF/blob/main/LiquidAI_LFM2-1.2B-Extract-IQ2_M.gguf) | IQ2_M | 0.43GB | 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/LiquidAI_LFM2-1.2B-Extract-GGUF --include "LiquidAI_LFM2-1.2B-Extract-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/LiquidAI_LFM2-1.2B-Extract-GGUF --include "LiquidAI_LFM2-1.2B-Extract-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (LiquidAI_LFM2-1.2B-Extract-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}