commit 2e8b5cefa00eef4e426c486b5c9549e7a27be6fc Author: ModelHub XC Date: Sun Jun 21 01:04:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ed545d9 --- /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 +dehallucinated-llama-3.2-8b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +dehallucinated-llama-3.2-8b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +dehallucinated-llama-3.2-8b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +dehallucinated-llama-3.2-8b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dehallucinated-llama-3.2-8b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dehallucinated-llama-3.2-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dehallucinated-llama-3.2-8b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dehallucinated-llama-3.2-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dehallucinated-llama-3.2-8b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dehallucinated-llama-3.2-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +dehallucinated-llama-3.2-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +dehallucinated-llama-3.2-8b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6eb22a0 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: hirundo-io/dehallucinated-llama-3.2-8b-instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/hirundo-io/dehallucinated-llama-3.2-8b-instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-i1-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/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/dehallucinated-llama-3.2-8b-instruct-GGUF/resolve/main/dehallucinated-llama-3.2-8b-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. + + diff --git a/dehallucinated-llama-3.2-8b-instruct.IQ4_XS.gguf b/dehallucinated-llama-3.2-8b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..31e3c8a --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25350d808d819c18fba54331156e83706fff837a9f242e02027a036c96d75a5c +size 1840906784 diff --git a/dehallucinated-llama-3.2-8b-instruct.Q2_K.gguf b/dehallucinated-llama-3.2-8b-instruct.Q2_K.gguf new file mode 100644 index 0000000..ffe7a4f --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d128af2023cfa85c5d48f0635ba9091e5c043bccc1ef8c54506c32a9de34a63b +size 1363935776 diff --git a/dehallucinated-llama-3.2-8b-instruct.Q3_K_L.gguf b/dehallucinated-llama-3.2-8b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..6b44bae --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a7399eab8ca28480374cb20f6095f840d13c124c04f956753cc4f86dabdb9d0 +size 1815347744 diff --git a/dehallucinated-llama-3.2-8b-instruct.Q3_K_M.gguf b/dehallucinated-llama-3.2-8b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..6992dd7 --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8138564145ee1b3f986cb3972eb699c56f1af9b69dcdc66c6724d83366dc82 +size 1687159328 diff --git a/dehallucinated-llama-3.2-8b-instruct.Q3_K_S.gguf b/dehallucinated-llama-3.2-8b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..a684082 --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbc9291106e422c1e339d958efee613911dc79509a909d743e5f04b6ffb8d1c7 +size 1542849056 diff --git a/dehallucinated-llama-3.2-8b-instruct.Q4_K_M.gguf b/dehallucinated-llama-3.2-8b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..b2b9c39 --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e51a21ae5920045f5eb9a7536410f13538b7edf28db65e051f14099b580431c7 +size 2019377696 diff --git a/dehallucinated-llama-3.2-8b-instruct.Q4_K_S.gguf b/dehallucinated-llama-3.2-8b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..82ca91c --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072ce13d7c4abbf2a515e94e2a645ca2997639948632ab4f0bab1de78efc7f6c +size 1928200736 diff --git a/dehallucinated-llama-3.2-8b-instruct.Q5_K_M.gguf b/dehallucinated-llama-3.2-8b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..5078bf4 --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d76abf572bfc44bcae4d4fd11bc552bb254980293a021cb52c7e6d0c83eb97d0 +size 2322154016 diff --git a/dehallucinated-llama-3.2-8b-instruct.Q5_K_S.gguf b/dehallucinated-llama-3.2-8b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..762db30 --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46d093cb9010f3ddfa34711051a4855d449e1670ba5b82275bc53a8e9b4c5102 +size 2269512224 diff --git a/dehallucinated-llama-3.2-8b-instruct.Q6_K.gguf b/dehallucinated-llama-3.2-8b-instruct.Q6_K.gguf new file mode 100644 index 0000000..680ca62 --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0ea60603ab87fe940164a3f6e72f8d19f025b81999bc35d0b50ceddb7c4fd97 +size 2643853856 diff --git a/dehallucinated-llama-3.2-8b-instruct.Q8_0.gguf b/dehallucinated-llama-3.2-8b-instruct.Q8_0.gguf new file mode 100644 index 0000000..482cda1 --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6880cbb97f164f2ede46b0012d05744c81d142bc92dbe56985f45b21b8c7e8f6 +size 3421899296 diff --git a/dehallucinated-llama-3.2-8b-instruct.f16.gguf b/dehallucinated-llama-3.2-8b-instruct.f16.gguf new file mode 100644 index 0000000..f0f5890 --- /dev/null +++ b/dehallucinated-llama-3.2-8b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a16ecc081c095bb05349867557975ebf832b3e8c8a61a71e3bca3aaa4d698aed +size 6433688096