commit 62d3b9c9862eb2047a44d165dd13606dc26efef7 Author: ModelHub XC Date: Mon Jun 15 22:52:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f6aca7d --- /dev/null +++ b/.gitattributes @@ -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 +*.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 +ErselFit_Finetuned_LLaMA_V2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ErselFit_Finetuned_LLaMA_V2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ErselFit_Finetuned_LLaMA_V2.f16.gguf filter=lfs diff=lfs merge=lfs -text +ErselFit_Finetuned_LLaMA_V2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ErselFit_Finetuned_LLaMA_V2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ErselFit_Finetuned_LLaMA_V2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ErselFit_Finetuned_LLaMA_V2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ErselFit_Finetuned_LLaMA_V2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ErselFit_Finetuned_LLaMA_V2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ErselFit_Finetuned_LLaMA_V2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ErselFit_Finetuned_LLaMA_V2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ErselFit_Finetuned_LLaMA_V2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ErselFit_Finetuned_LLaMA_V2.IQ4_XS.gguf b/ErselFit_Finetuned_LLaMA_V2.IQ4_XS.gguf new file mode 100644 index 0000000..5d22b43 --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35da5265e4680683406c92e9008110aea91477dbec7643e044e8de72cb5099a6 +size 4484362848 diff --git a/ErselFit_Finetuned_LLaMA_V2.Q2_K.gguf b/ErselFit_Finetuned_LLaMA_V2.Q2_K.gguf new file mode 100644 index 0000000..55c032a --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:737bd0a580980eccc18b816f0e27fbf6a681a8db82e1110c9c84845ffc852d0a +size 3179131488 diff --git a/ErselFit_Finetuned_LLaMA_V2.Q3_K_L.gguf b/ErselFit_Finetuned_LLaMA_V2.Q3_K_L.gguf new file mode 100644 index 0000000..a64ace3 --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67487f12cd31ae87453c7daa4295264bbe38c18773fa141830ba31e043655644 +size 4321956448 diff --git a/ErselFit_Finetuned_LLaMA_V2.Q3_K_M.gguf b/ErselFit_Finetuned_LLaMA_V2.Q3_K_M.gguf new file mode 100644 index 0000000..3486cf8 --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b2b2d8a75c8f4c95dd211a4a21fafe9d6abeb137b1fe030df7287da5b599f41 +size 4018917984 diff --git a/ErselFit_Finetuned_LLaMA_V2.Q3_K_S.gguf b/ErselFit_Finetuned_LLaMA_V2.Q3_K_S.gguf new file mode 100644 index 0000000..e27a27c --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5421cffdc9d9354e17b45f67e19992cb75526f32916dfe7180f1be8405a98cbe +size 3664499296 diff --git a/ErselFit_Finetuned_LLaMA_V2.Q4_K_M.gguf b/ErselFit_Finetuned_LLaMA_V2.Q4_K_M.gguf new file mode 100644 index 0000000..3aea097 --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf5aa833d5a10f0a67d7a7e049c5857fd90d28236c4f602039eed09ef1767222 +size 4920734304 diff --git a/ErselFit_Finetuned_LLaMA_V2.Q4_K_S.gguf b/ErselFit_Finetuned_LLaMA_V2.Q4_K_S.gguf new file mode 100644 index 0000000..cb9a7b2 --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e47596b479fcdb639dbecb99f0fce173d761e988a0a4905031c078e363b2128a +size 4692669024 diff --git a/ErselFit_Finetuned_LLaMA_V2.Q5_K_M.gguf b/ErselFit_Finetuned_LLaMA_V2.Q5_K_M.gguf new file mode 100644 index 0000000..c33953b --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8088e82761a6c207b91dd75e4207b78da5a791f1f99939ea7a20c1a652a29fa3 +size 5732987488 diff --git a/ErselFit_Finetuned_LLaMA_V2.Q5_K_S.gguf b/ErselFit_Finetuned_LLaMA_V2.Q5_K_S.gguf new file mode 100644 index 0000000..011ea5a --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af278e700f9bcc08d2673b741ea5cab73d0b7673dccd935abd50bec7d9841b67 +size 5599294048 diff --git a/ErselFit_Finetuned_LLaMA_V2.Q6_K.gguf b/ErselFit_Finetuned_LLaMA_V2.Q6_K.gguf new file mode 100644 index 0000000..ad9dde1 --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19020ffe4f39fefc04b59d9268db09a356cbdaaa42d52d6ef717d2c3e72ebeb1 +size 6596006496 diff --git a/ErselFit_Finetuned_LLaMA_V2.Q8_0.gguf b/ErselFit_Finetuned_LLaMA_V2.Q8_0.gguf new file mode 100644 index 0000000..3b3e2e1 --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ccd9412eaa2b62a3c733b3cf6f20348026db20c415cc5b2dc848aa42485a5b6 +size 8540770912 diff --git a/ErselFit_Finetuned_LLaMA_V2.f16.gguf b/ErselFit_Finetuned_LLaMA_V2.f16.gguf new file mode 100644 index 0000000..65c810d --- /dev/null +++ b/ErselFit_Finetuned_LLaMA_V2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8c3c8a99ae47071591a66f411aa8f1b9ca95cc0a3b04bcfd47893e608f9c938 +size 16068891232 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fbae5b4 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: Ersel1/ErselFit_Finetuned_LLaMA_8B_V2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Ersel1/ErselFit_Finetuned_LLaMA_8B_V2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ErselFit_Finetuned_LLaMA_V2-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ErselFit_Finetuned_LLaMA_V2-GGUF/resolve/main/ErselFit_Finetuned_LLaMA_V2.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +