初始化项目，由ModelHub XC社区提供模型

Model: mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,60 @@
+*.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
+imatrix.dat filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama_3.2_3b_Kermes_v2.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

Llama_3.2_3b_Kermes_v2.1.i1-IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a3f6bf520cb9c8eda623b4a205e40a4e0fb32478954b4a8d65f2e239ef8836
+size 924188224

Llama_3.2_3b_Kermes_v2.1.i1-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab06cac81bebd9bc43519f382b871d88e277d566baf96428346b2ed59003468d
+size 868154944

Llama_3.2_3b_Kermes_v2.1.i1-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1382a4f2bdda06dbaccc8615dbb785f7d830f6f8968237386cb49ece6cd4801e
+size 1229028928

Llama_3.2_3b_Kermes_v2.1.i1-IQ2_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c476c3c731627f506e290ab8666d47b70adb5753e1c6f7aade9a51da4329abc6
+size 1154317888

Llama_3.2_3b_Kermes_v2.1.i1-IQ2_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c099410a7fa0714bc0af9519ae135de5af688456dbc1d6b8f7ebd00820193931
+size 1100545600

Llama_3.2_3b_Kermes_v2.1.i1-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a7b582431b5b50469e5a81e30f8af3d498988477019716db010153990721119
+size 1017577024

Llama_3.2_3b_Kermes_v2.1.i1-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0776948b8d7c7597e4248c750a306a21bb6cf21c1cbc7c7bc505609ca84cc2a3
+size 1599665728

Llama_3.2_3b_Kermes_v2.1.i1-IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:195a9d6b7476cf1cc7b4620da0244f69399d631ca6e0d6b163a88e2725835378
+size 1542846016

Llama_3.2_3b_Kermes_v2.1.i1-IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fba8895cc7522ba48e8f1333f64b8769aed963478155d5b97f71bbee62173a45
+size 1476785728

Llama_3.2_3b_Kermes_v2.1.i1-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f002fecd4a1d7f64376c0e62c9af455aca7a26382ab6435a267e649cabbd5bb
+size 1348763200

Llama_3.2_3b_Kermes_v2.1.i1-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d28d19c02c64c8220296925d627f8941841d0e3b08dfb3fa6be1e6ecd48e34
+size 1917187648

Llama_3.2_3b_Kermes_v2.1.i1-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a10eadf0ea5f35236dd238c6850fae3519f1c65c274c8612d103ed0167774a
+size 1829107264

Llama_3.2_3b_Kermes_v2.1.i1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ac248eb2296d6a65e2a99c10fb24abd456c3559a161435080e0a4e3a3160b3
+size 1363932736

Llama_3.2_3b_Kermes_v2.1.i1-Q2_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785239ad6f7beb6ce88e01636ac0c89e3d6c8900b56a9c06ff23c16533b9e000
+size 1274279488

Llama_3.2_3b_Kermes_v2.1.i1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835640ff91b77cc203c9cfc3dfb39e9d88ebff21bee6190be7170647ccaf7572
+size 1815344704

Llama_3.2_3b_Kermes_v2.1.i1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff478bdbe1db3c2b7dd8f1b579457b5aa0f3aeaec779ee549197c1c4c0773079
+size 1687156288

Llama_3.2_3b_Kermes_v2.1.i1-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716cf5423e2151a756a636095f0eecc284da290a6c24ea5467b87fb6315f7a4c
+size 1542846016

Llama_3.2_3b_Kermes_v2.1.i1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f0ff9bd0e58d7e789481c2e4f7d260adb3c4cd46e5da9b5f6e9981b9efd3ee
+size 1921906240

Llama_3.2_3b_Kermes_v2.1.i1-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2343d9d7585ea09cf673f394dcc37904e6bd5d1f51cb0009b061b4372ed6e88
+size 2093348416

Llama_3.2_3b_Kermes_v2.1.i1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d42e4f712aaaab0d309c5e2bff8a6d8b785e61629bccf005573db7c3dbb005b
+size 2019374656

Llama_3.2_3b_Kermes_v2.1.i1-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f238a89c28b1adaaa5125dc6af3bbe33054106128cfcee22589ea246dc9b4d22
+size 1928197696

Llama_3.2_3b_Kermes_v2.1.i1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903be92a578429d8f555d14a060fd2f085ff01d7ca67007dd1dcee1aec1e9735
+size 2322150976

Llama_3.2_3b_Kermes_v2.1.i1-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06925665482c7193283865a2762938fe9b74bad1a4ff20b6baa7a47e78acd1e2
+size 2269509184

Llama_3.2_3b_Kermes_v2.1.i1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c05150cf9dc96a742e7174c006036258a0078ea30e4886fa6766633f39b3f9
+size 2643850816

README.md

@@ -0,0 +1,79 @@
+---
+base_model: Nexesenex/Llama_3.2_3b_Kermes_v2.1
+language:
+- en
+library_name: transformers
+license: llama3.2
+quantized_by: mradermacher
+tags:
+- mergekit
+- merge
+---
+## About
+
+<!-- ### quantize_version: 2 -->
+<!-- ### output_tensor_quantised: 1 -->
+<!-- ### convert_type: hf -->
+<!-- ### vocab_type:  -->
+<!-- ### tags: nicoboss -->
+weighted/imatrix quants of https://huggingface.co/Nexesenex/Llama_3.2_3b_Kermes_v2.1
+
+<!-- provided-files -->
+static quants are available at https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF
+## 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/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ1_S.gguf) | i1-IQ1_S | 1.0 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ1_M.gguf) | i1-IQ1_M | 1.0 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.1 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ2_S.gguf) | i1-IQ2_S | 1.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ2_M.gguf) | i1-IQ2_M | 1.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.4 | very low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.4 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q2_K.gguf) | i1-Q2_K | 1.5 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ3_S.gguf) | i1-IQ3_S | 1.6 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.6 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ3_M.gguf) | i1-IQ3_M | 1.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.8 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.9 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.0 | prefer IQ4_XS |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q4_0.gguf) | i1-Q4_0 | 2.0 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.0 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.1 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q4_1.gguf) | i1-Q4_1 | 2.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF/resolve/main/Llama_3.2_3b_Kermes_v2.1.i1-Q6_K.gguf) | i1-Q6_K | 2.7 | practically like static Q6_K |
+
+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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
+
+<!-- end -->

imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f26df81fe2d7c91d9979ca39b7e8d813ed72110945d1786d8be561b702d8d6f
+size 2988377