commit 2888343f55b7fd02a1731a4e753a65fe86ef5af9 Author: ModelHub XC Date: Sat Apr 11 03:16:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Falcon3-3B-Instruct-abliterated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c9cca82 --- /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 +Falcon3-3B-Instruct-abliterated.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-3B-Instruct-abliterated.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-3B-Instruct-abliterated.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-3B-Instruct-abliterated.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-3B-Instruct-abliterated.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-3B-Instruct-abliterated.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-3B-Instruct-abliterated.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-3B-Instruct-abliterated.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-3B-Instruct-abliterated.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-3B-Instruct-abliterated.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-3B-Instruct-abliterated.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-3B-Instruct-abliterated.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Falcon3-3B-Instruct-abliterated.IQ4_XS.gguf b/Falcon3-3B-Instruct-abliterated.IQ4_XS.gguf new file mode 100644 index 0000000..56018de --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32791911c04fa6ebed7e741021a5164a5599f2fa8d5dfadf60363e2a5e980097 +size 1845154336 diff --git a/Falcon3-3B-Instruct-abliterated.Q2_K.gguf b/Falcon3-3B-Instruct-abliterated.Q2_K.gguf new file mode 100644 index 0000000..ea7a4a1 --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:854298f7424a39c258336a2dfe666bfef7220e61429e391e57b1aac7a73ec3cd +size 1353880096 diff --git a/Falcon3-3B-Instruct-abliterated.Q3_K_L.gguf b/Falcon3-3B-Instruct-abliterated.Q3_K_L.gguf new file mode 100644 index 0000000..ae51498 --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf9b339f45718e9c7c52a075ac3e7b66792165e95e11f3c7c04dd11e7fa58964 +size 1781355040 diff --git a/Falcon3-3B-Instruct-abliterated.Q3_K_M.gguf b/Falcon3-3B-Instruct-abliterated.Q3_K_M.gguf new file mode 100644 index 0000000..6534285 --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86a8ed1bfdeebbc2a70900511847a5f35188bd92c7d3ba2f02f991198751ef13 +size 1673220640 diff --git a/Falcon3-3B-Instruct-abliterated.Q3_K_S.gguf b/Falcon3-3B-Instruct-abliterated.Q3_K_S.gguf new file mode 100644 index 0000000..d2ed902 --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee9f72078983bf5c8730d767b044754897246360e25ea5884905bb25f4e1f81 +size 1549406752 diff --git a/Falcon3-3B-Instruct-abliterated.Q4_K_M.gguf b/Falcon3-3B-Instruct-abliterated.Q4_K_M.gguf new file mode 100644 index 0000000..8d71259 --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a488fd1de905ba362b8d3ee53f4660c6c795bb40a74bd7c45cf3552792eb4ff8 +size 2005684768 diff --git a/Falcon3-3B-Instruct-abliterated.Q4_K_S.gguf b/Falcon3-3B-Instruct-abliterated.Q4_K_S.gguf new file mode 100644 index 0000000..c881fb7 --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2b876d68db515e6394bebce268284b841df2034c682f4e2c5f0e5f94392faf9 +size 1933234720 diff --git a/Falcon3-3B-Instruct-abliterated.Q5_K_M.gguf b/Falcon3-3B-Instruct-abliterated.Q5_K_M.gguf new file mode 100644 index 0000000..9ef2426 --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d905a9effc27f2f22c848dd48d2a45bc07af81c25c44bbad7fbbfbfefd4f1d4 +size 2319471136 diff --git a/Falcon3-3B-Instruct-abliterated.Q5_K_S.gguf b/Falcon3-3B-Instruct-abliterated.Q5_K_S.gguf new file mode 100644 index 0000000..8d2815a --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec5e1e756dea249b7ffcf37b6a80fb192875d7fb9609e1c5607ddb9ba16fb5f5 +size 2277691936 diff --git a/Falcon3-3B-Instruct-abliterated.Q6_K.gguf b/Falcon3-3B-Instruct-abliterated.Q6_K.gguf new file mode 100644 index 0000000..6ee5415 --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32479971067035d6062c76b40ec009f26352a4a06e7c712a848346a1263d7f42 +size 2652869152 diff --git a/Falcon3-3B-Instruct-abliterated.Q8_0.gguf b/Falcon3-3B-Instruct-abliterated.Q8_0.gguf new file mode 100644 index 0000000..73fed30 --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a354a68716408e1b111b7984a7f5c80db7f2ff12789062883ed6c84311760ca0 +size 3434533408 diff --git a/Falcon3-3B-Instruct-abliterated.f16.gguf b/Falcon3-3B-Instruct-abliterated.f16.gguf new file mode 100644 index 0000000..2835de1 --- /dev/null +++ b/Falcon3-3B-Instruct-abliterated.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e762e6d952280b06283c5856e25b2d95215c47e4e3cdb96a553543937bdb322e +size 6460330528 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2dedb71 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: huihui-ai/Falcon3-3B-Instruct-abliterated +language: +- en +- fr +- es +- pt +library_name: transformers +license: other +license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html +license_name: falcon-llm-license +quantized_by: mradermacher +tags: +- falcon3 +- abliterated +- uncensored +--- +## About + + + + + + +static quants of https://huggingface.co/huihui-ai/Falcon3-3B-Instruct-abliterated + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-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/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.Q6_K.gguf) | Q6_K | 2.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-3B-Instruct-abliterated-GGUF/resolve/main/Falcon3-3B-Instruct-abliterated.f16.gguf) | f16 | 6.6 | 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. + +