初始化项目，由ModelHub XC社区提供模型

Model: bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF
Source: Original Platform

.gitattributes

@@ -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
+
+LiquidAI_LFM2.5-1.2B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text

LiquidAI_LFM2.5-1.2B-Instruct-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21bd4c41928b378578501bd4b85b3fdd643420cd605e9b2ddba036d88517904f
+size 434132320

LiquidAI_LFM2.5-1.2B-Instruct-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b10224c2d57f738d2693260da5988a39fad174330d2921d5702b371452deca
+size 566793568

LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54256819b3b96864c8e2fb22d56ae17284ac23ea58526f9b8332cca48f4c0d4f
+size 537810272

LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ddfe2cf991cea6aca304b3a73019d0d83e2a186fdcd0c47c11f6c30845e9c6
+size 490984800

LiquidAI_LFM2.5-1.2B-Instruct-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0eca2e29e6b6cd00166d2434d3a18acdff07c7b90a70c417d3756ff492df4f
+size 695752032

LiquidAI_LFM2.5-1.2B-Instruct-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a310da4b2d5b0604d182a30157fba22c3fe2084c8c0499e9d0bc44bb9feea115
+size 663377248

LiquidAI_LFM2.5-1.2B-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6bd453f21801b3ccc703687b8f2b6e61d8bc5af699fe2c97cdce7b3871e81e8
+size 483399008

LiquidAI_LFM2.5-1.2B-Instruct-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35451a37110064bbb2d8e0a84571005712826c9b2c753b95e8e16b54071ed8ac
+size 515904864

LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a68b55c3f9e4d281f4cb728f39de1f84482ceb4a7f88ac4e3c04e595fe8799b
+size 635475296

LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d09f0fbb0c0ad34e0ff48c8c8dd497b4b500c030445779c8cd7d9e1bcafd8f
+size 600348000

LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5afdb68ac0ccaf218225b28dd3ee80686e01f328d3f9a95660197f339b68fe
+size 558159200

LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bab2821aae5898d3be43d9a6f8281b3390e6c7b7e41a852dd185f802f5e7e57
+size 667981152

LiquidAI_LFM2.5-1.2B-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bbc363613e2c47a7c33ca001dd9190009417d9bebadd07b98bdcf4aa0f5553b
+size 697849184

LiquidAI_LFM2.5-1.2B-Instruct-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:177e6b8bb0630ea35561f18d2844acacc80ac929fbd17e6deb6950191cf3a128
+size 760501600

LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e424c25257fdf7bdc6507d6e2b82ba7a6d4668c9f16aea2531c459f671a66482
+size 763401568

LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baaf531531f397456e46b89554fd66f30ec84b57d5b0cfd6365785cd3db12a97
+size 730895712

LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35bd1bcf1839b8e7a6ed7f8bb85a98340286f57144cb160963a74c86752bc91
+size 700470624

LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab109acbc6615b21a9a689e8df8fd0bca93bb12d03ea85a4da4134d3b6970f3
+size 875861344

LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c679b8a8c1855937d38d643479384eeaa4ba7d3a5014c0417382fdf4f362509
+size 843355488

LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30008e5b2ec8660f9c3d405bf9c3349ab9892721916e3a5fe4ce2d75417a9b8a
+size 825251168

LiquidAI_LFM2.5-1.2B-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00334bb7ac776739b1a1167be31f8b57002ca5033b05c67eecb164d43b7d6e2a
+size 962844000

LiquidAI_LFM2.5-1.2B-Instruct-Q6_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdffc7eaacf9de13e993904c9965235070173f530bf536e27a5f7ba9c3459100
+size 995349856

LiquidAI_LFM2.5-1.2B-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d94fbe158d173444ad2b95c4c90845784ec04a0c918190aa029e3c4fc2e42f
+size 1246254432

LiquidAI_LFM2.5-1.2B-Instruct-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800ce028a8b3af993c1292ffbd781904cdc18d7a2514d75de807ca668dabb662
+size 2343326784

LiquidAI_LFM2.5-1.2B-Instruct-imatrix.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf6afd3f20515f1acb013ac2e5a0d53a6d5803a0479109fa0d756e2ed87f59c
+size 1161536

README.md

@@ -0,0 +1,193 @@
+---
+quantized_by: bartowski
+pipeline_tag: text-generation
+license_link: LICENSE
+license_name: lfm1.0
+tags:
+- liquid
+- lfm2.5
+- edge
+base_model_relation: quantized
+base_model: LiquidAI/LFM2.5-1.2B-Instruct
+license: other
+language:
+- en
+- ar
+- zh
+- fr
+- de
+- ja
+- ko
+- es
+---
+
+## Llamacpp imatrix Quantizations of LFM2.5-1.2B-Instruct 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/b7610">b7610</a> for quantization.
+
+Original model: https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct
+
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d)
+
+Run them in your choice of tools:
+
+- [llama.cpp](https://github.com/ggml-org/llama.cpp)
+- [LM Studio](https://lmstudio.ai/)
+- [koboldcpp](https://github.com/LostRuins/koboldcpp)
+- [Jan AI](https://www.jan.ai/)
+- [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui)
+- [LoLLMs](https://github.com/ParisNeo/lollms)
+
+Note: if it's a newly supported model, you may need to wait for an update from the developers.
+
+## Prompt format
+
+```
+<|startoftext|><|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 |
+| -------- | ---------- | --------- | ----- | ----------- |
+| [LFM2.5-1.2B-Instruct-bf16.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-bf16.gguf) | bf16 | 2.34GB | false | Full BF16 weights. |
+| [LFM2.5-1.2B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q8_0.gguf) | Q8_0 | 1.25GB | false | Extremely high quality, generally unneeded but max available quant. |
+| [LFM2.5-1.2B-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q6_K_L.gguf) | Q6_K_L | 1.00GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
+| [LFM2.5-1.2B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q6_K.gguf) | Q6_K | 0.96GB | false | Very high quality, near perfect, *recommended*. |
+| [LFM2.5-1.2B-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_L.gguf) | Q5_K_L | 0.88GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
+| [LFM2.5-1.2B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_M.gguf) | Q5_K_M | 0.84GB | false | High quality, *recommended*. |
+| [LFM2.5-1.2B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q5_K_S.gguf) | Q5_K_S | 0.83GB | false | High quality, *recommended*. |
+| [LFM2.5-1.2B-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_L.gguf) | Q4_K_L | 0.76GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [LFM2.5-1.2B-Instruct-Q4_1.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q4_1.gguf) | Q4_1 | 0.76GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
+| [LFM2.5-1.2B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_M.gguf) | Q4_K_M | 0.73GB | false | Good quality, default size for most use cases, *recommended*. |
+| [LFM2.5-1.2B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q4_K_S.gguf) | Q4_K_S | 0.70GB | false | Slightly lower quality with more space savings, *recommended*. |
+| [LFM2.5-1.2B-Instruct-Q4_0.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q4_0.gguf) | Q4_0 | 0.70GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
+| [LFM2.5-1.2B-Instruct-IQ4_NL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-IQ4_NL.gguf) | IQ4_NL | 0.70GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
+| [LFM2.5-1.2B-Instruct-Q3_K_XL.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-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. |
+| [LFM2.5-1.2B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-IQ4_XS.gguf) | IQ4_XS | 0.66GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [LFM2.5-1.2B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_L.gguf) | Q3_K_L | 0.64GB | false | Lower quality but usable, good for low RAM availability. |
+| [LFM2.5-1.2B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_M.gguf) | Q3_K_M | 0.60GB | false | Low quality. |
+| [LFM2.5-1.2B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-IQ3_M.gguf) | IQ3_M | 0.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [LFM2.5-1.2B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q3_K_S.gguf) | Q3_K_S | 0.56GB | false | Low quality, not recommended. |
+| [LFM2.5-1.2B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XS.gguf) | IQ3_XS | 0.54GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
+| [LFM2.5-1.2B-Instruct-Q2_K_L.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q2_K_L.gguf) | Q2_K_L | 0.52GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [LFM2.5-1.2B-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 0.49GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [LFM2.5-1.2B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-Q2_K.gguf) | Q2_K | 0.48GB | false | Very low quality but surprisingly usable. |
+| [LFM2.5-1.2B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/LiquidAI_LFM2.5-1.2B-Instruct-GGUF/blob/main/LiquidAI_LFM2.5-1.2B-Instruct-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_LFM2.5-1.2B-Instruct-GGUF --include "LiquidAI_LFM2.5-1.2B-Instruct-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_LFM2.5-1.2B-Instruct-GGUF --include "LiquidAI_LFM2.5-1.2B-Instruct-Q8_0/*" --local-dir ./
+```
+
+You can either specify a new local-dir (LiquidAI_LFM2.5-1.2B-Instruct-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

configuration.json

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