commit 4f69e443f0bb02fef66d0241c01435ae6f680372 Author: ModelHub XC Date: Wed Oct 21 20:26:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..85cbab7 --- /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 +Grok_HumanLike_Llama-3.2-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Grok_HumanLike_Llama-3.2-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Grok_HumanLike_Llama-3.2-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Grok_HumanLike_Llama-3.2-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Grok_HumanLike_Llama-3.2-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Grok_HumanLike_Llama-3.2-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Grok_HumanLike_Llama-3.2-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Grok_HumanLike_Llama-3.2-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Grok_HumanLike_Llama-3.2-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.IQ4_XS.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..e43bbcf --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:255c180f39e52c40442a420bd0685c2bc5cecdb4c7d3bff0c3e7ad978981d369 +size 1840907328 diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.Q2_K.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..6e23581 --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1e7161c22e5c93f58b743f9264fabee2f390c0713481e5165defd58d87f7316 +size 1363936320 diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_L.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..1970274 --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50e0bbbfde8594943600561ee9c919516709cccdcf9bd953ede5a750d9db39bf +size 1815348288 diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_M.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..c5a032b --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce7dde74ebe4bb5ce9cb8f7c97ba1499e6b4cf041a3fc5594046894a168ab19 +size 1687159872 diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_S.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..3fe274d --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcbe160e9c2ce9ad9207e174de8f21dea8146e39b55ceeeed0de66fa68e74d07 +size 1542849600 diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.Q4_K_M.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..551247e --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e27112536e309adc18cedcd1a29aa59c6e391e54b974c47d6520c0d35a4beb0 +size 2019378240 diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.Q4_K_S.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..acf692f --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faba7e5d7e7430c7602372b3e1c6b7406d1a1c507869b07afb7e460b402152cc +size 1928201280 diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.Q5_K_M.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..19a302d --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be0826e7e05cbf42ddb9e0ec342aba3c939d35d03bdcdf4d427973c8ecb8cd2 +size 2322154560 diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.Q5_K_S.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..fd717a2 --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98e082248fd89f77931e4b45c75278459873eed7a9d5ada19d4886269cf74949 +size 2269512768 diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.Q6_K.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..9c7eeba --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba46336974482ff89c7213f56e067d7b92019aeeb897ddeb6aeff3f23b251ca +size 2643854400 diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.Q8_0.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..c66cd6e --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce977e7af802da168573161d91acf1723f2fc11a19a74a445c6ad11bdf790279 +size 3421899840 diff --git a/Grok_HumanLike_Llama-3.2-3B-Instruct.f16.gguf b/Grok_HumanLike_Llama-3.2-3B-Instruct.f16.gguf new file mode 100644 index 0000000..5d2960a --- /dev/null +++ b/Grok_HumanLike_Llama-3.2-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76e293b180312e43979b69fab019829e67b52f3e1bbcd7125c7ae8661a6205a7 +size 6433688640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fe5330d --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: tungdqzenai/Grok_HumanLike_Llama-3.2-3B-Instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/tungdqzenai/Grok_HumanLike_Llama-3.2-3B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Grok_HumanLike_Llama-3.2-3B-Instruct-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/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Grok_HumanLike_Llama-3.2-3B-Instruct-GGUF/resolve/main/Grok_HumanLike_Llama-3.2-3B-Instruct.f16.gguf) | f16 | 6.5 | 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. + +