commit f056efe303527cb7a1591dd0fe72ba65c012aa9e Author: ModelHub XC Date: Tue Apr 21 19:40:54 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7b35c23 --- /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 +Vikhr-Llama-3.2-1B-Instruct-abliterated.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-Llama-3.2-1B-Instruct-abliterated.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-Llama-3.2-1B-Instruct-abliterated.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-Llama-3.2-1B-Instruct-abliterated.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-Llama-3.2-1B-Instruct-abliterated.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-Llama-3.2-1B-Instruct-abliterated.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-Llama-3.2-1B-Instruct-abliterated.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-Llama-3.2-1B-Instruct-abliterated.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-Llama-3.2-1B-Instruct-abliterated.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..38eb3a5 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct-abliterated +language: +- ru +- en +library_name: transformers +license: llama3.2 +model_name: Vikhr-Llama-3.2-1B-Instruct-abliterated +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- not-for-all-audiences +--- +## About + + + + + + +static quants of https://huggingface.co/Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct-abliterated + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Vikhr-Llama-3.2-1B-Instruct-abliterated-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/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-Llama-3.2-1B-Instruct-abliterated-GGUF/resolve/main/Vikhr-Llama-3.2-1B-Instruct-abliterated.f16.gguf) | f16 | 2.6 | 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. + + diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.IQ4_XS.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.IQ4_XS.gguf new file mode 100644 index 0000000..2f87e33 --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c087d96f6023350780dff64224f00f742b0c665e0b61f7a9e0366ad30fde9a +size 748384896 diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q2_K.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q2_K.gguf new file mode 100644 index 0000000..1dc6023 --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83453ef7bcd70fdcf5d85edea882fc968fee8054d501bac03f29b915622cf68e +size 580874880 diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_L.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_L.gguf new file mode 100644 index 0000000..92a507f --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c165b6f3c4da2b73b2909f8add579535686eaf0c480dc89a11a32106de766a76 +size 732525184 diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_M.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_M.gguf new file mode 100644 index 0000000..870e545 --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e28ea9bc06374ecdafb0fc0aa494c6220fdd22eb3fe706f0f8975694deec2ec5 +size 690844288 diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_S.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_S.gguf new file mode 100644 index 0000000..7e2202b --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d2ba793ce5d5d47b229ac4bd24f3fad4ef582c67e7494c27842c1e5b12def4 +size 641692288 diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q4_K_M.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q4_K_M.gguf new file mode 100644 index 0000000..7d6e04e --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bffe849ab5f47b780304807f3234d7640171b5b8025030a78f4df8b7b06d73c7 +size 807694976 diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q4_K_S.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q4_K_S.gguf new file mode 100644 index 0000000..7b0a691 --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49d313848495baa3b8a52e1318b7e7a2a9c741f4a911e82697d39e95d5683fa2 +size 775647872 diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q5_K_M.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q5_K_M.gguf new file mode 100644 index 0000000..d965810 --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f6002b4fb62af0d69f491718793438c93dacf775f966daeb90dae425cac6d4c +size 911504000 diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q5_K_S.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q5_K_S.gguf new file mode 100644 index 0000000..1aff2e2 --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:486ee824050fca1cccc4eb06391da9de46901ea541e34fefb7b4a0d510d6f28e +size 892564096 diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q6_K.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q6_K.gguf new file mode 100644 index 0000000..cd13db7 --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b92acfb47ad0e4cbb3849c05e15a83f956a1dd96b09a3a2f72b0ff9c85a15240 +size 1021801088 diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q8_0.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q8_0.gguf new file mode 100644 index 0000000..460c72a --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f3f3ad7ca064df2b542cf9b4e323ecc808f7beb7c57d0c932f0d6c6f67d3405 +size 1321083520 diff --git a/Vikhr-Llama-3.2-1B-Instruct-abliterated.f16.gguf b/Vikhr-Llama-3.2-1B-Instruct-abliterated.f16.gguf new file mode 100644 index 0000000..d841a4d --- /dev/null +++ b/Vikhr-Llama-3.2-1B-Instruct-abliterated.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98eb503859321456de6b96a7aa999d5ace9fb377b270f4feac33543a2015ff42 +size 2479596160