commit 2cb78dc1fca075b424093aa5aac0b01d81a6c443 Author: ModelHub XC Date: Tue Sep 8 09:52:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cf5519a --- /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 +Llama-3.2-1B-Instruct-hikaye.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-hikaye.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-hikaye.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-hikaye.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-hikaye.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-hikaye.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-hikaye.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-hikaye.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-hikaye.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-hikaye.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-hikaye.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-hikaye.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-hikaye.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-hikaye.IQ4_XS.gguf new file mode 100644 index 0000000..18571a7 --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffd20c82279a18ae5c5c2281e7ae868dea451d27a20571a65e09818abfe88e8f +size 748384384 diff --git a/Llama-3.2-1B-Instruct-hikaye.Q2_K.gguf b/Llama-3.2-1B-Instruct-hikaye.Q2_K.gguf new file mode 100644 index 0000000..53846bc --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b9725ff4bf0b617a1e36020711dfef62a72242fb342e74517097a35366c215e +size 580874368 diff --git a/Llama-3.2-1B-Instruct-hikaye.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-hikaye.Q3_K_L.gguf new file mode 100644 index 0000000..aad947f --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddb5329408d9bba6d7174e46ff9863e95642e3f4b5f035b52701de941bff71e4 +size 732524672 diff --git a/Llama-3.2-1B-Instruct-hikaye.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-hikaye.Q3_K_M.gguf new file mode 100644 index 0000000..7c3aa65 --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d2100ecd9c9bebc789fe5344abfcb8e5ac65155bc795e82f4a2e7559f8f20a +size 690843776 diff --git a/Llama-3.2-1B-Instruct-hikaye.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-hikaye.Q3_K_S.gguf new file mode 100644 index 0000000..b30cb3c --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6b48f0bbc464a35905075f0c16735d944c6c2b04989f128344eca69d089bb1d +size 641691776 diff --git a/Llama-3.2-1B-Instruct-hikaye.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-hikaye.Q4_K_M.gguf new file mode 100644 index 0000000..e60b047 --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73184a638d7346370fd5f16b116d8a172cbd90f7877f02db8aa6837ad0dbcef +size 807694464 diff --git a/Llama-3.2-1B-Instruct-hikaye.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-hikaye.Q4_K_S.gguf new file mode 100644 index 0000000..404c935 --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c4f748f96c8c305c0e9163c29dd7882ec52c10de3bb968fd9132766ff35dccb +size 775647360 diff --git a/Llama-3.2-1B-Instruct-hikaye.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-hikaye.Q5_K_M.gguf new file mode 100644 index 0000000..7735669 --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c178fdb5d5af6c11901399d1e17c52d0ab30a6defbe1c0689f8d4fd07ab67521 +size 911503488 diff --git a/Llama-3.2-1B-Instruct-hikaye.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-hikaye.Q5_K_S.gguf new file mode 100644 index 0000000..41c8430 --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1266bbbec768ca5506475bc7e3f1fdfb81c7f4c0b9d4138e30300ab73cfefc56 +size 892563584 diff --git a/Llama-3.2-1B-Instruct-hikaye.Q6_K.gguf b/Llama-3.2-1B-Instruct-hikaye.Q6_K.gguf new file mode 100644 index 0000000..c174a57 --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c54293396530f9c4759229c76a18ddc8f3bfee016b37c9f1255c9c3f619b9533 +size 1021800576 diff --git a/Llama-3.2-1B-Instruct-hikaye.Q8_0.gguf b/Llama-3.2-1B-Instruct-hikaye.Q8_0.gguf new file mode 100644 index 0000000..86bd692 --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aecd54dfeb63c2862bfde51f355b7fb8a4e5524533034c02cd431c6047478f2 +size 1321083008 diff --git a/Llama-3.2-1B-Instruct-hikaye.f16.gguf b/Llama-3.2-1B-Instruct-hikaye.f16.gguf new file mode 100644 index 0000000..15795c7 --- /dev/null +++ b/Llama-3.2-1B-Instruct-hikaye.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a768b93bb452b7b7ad38d114ff56f7b463b5411d72d998a5e5202e3ebd9b48f +size 2479595648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e2a041f --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: arsalanaa/Llama-3.2-1B-Instruct-hikaye +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/arsalanaa/Llama-3.2-1B-Instruct-hikaye + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-Instruct-hikaye-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/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-hikaye-GGUF/resolve/main/Llama-3.2-1B-Instruct-hikaye.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. + +