commit a8b38af23cf67a28dd309ecd8105c81e87dd2c1c Author: ModelHub XC Date: Sat Aug 22 07:03:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/controllable-llama2-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d0223fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +controllable-llama2-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +controllable-llama2-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2eadcea --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: umd-zhou-lab/controllable-llama2-7b +language: +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/umd-zhou-lab/controllable-llama2-7b + + +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/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/controllable-llama2-7b-GGUF/resolve/main/controllable-llama2-7b.f16.gguf) | f16 | 13.6 | 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/controllable-llama2-7b.IQ3_M.gguf b/controllable-llama2-7b.IQ3_M.gguf new file mode 100644 index 0000000..0459baa --- /dev/null +++ b/controllable-llama2-7b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d78d441c3982aa0ec68d32139b52a48bb9fd8d7bd058eda45fb267d551c54f5 +size 3114870176 diff --git a/controllable-llama2-7b.IQ3_S.gguf b/controllable-llama2-7b.IQ3_S.gguf new file mode 100644 index 0000000..a4155b6 --- /dev/null +++ b/controllable-llama2-7b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ac6909405e45b53581b2d2f310013b113c83864a40f849a075bf6b41a246c8 +size 2948310432 diff --git a/controllable-llama2-7b.IQ3_XS.gguf b/controllable-llama2-7b.IQ3_XS.gguf new file mode 100644 index 0000000..2e83d43 --- /dev/null +++ b/controllable-llama2-7b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac66993a76d763376977ed03f8c6d66a83d7a3ddaf7211216d4f5ef55fc117bc +size 2796529056 diff --git a/controllable-llama2-7b.IQ4_XS.gguf b/controllable-llama2-7b.IQ4_XS.gguf new file mode 100644 index 0000000..d3af5c9 --- /dev/null +++ b/controllable-llama2-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d34f53acc24eee01feeba4d54fd51f1d47b451aab579fb3193bc46919d7e37e7 +size 3647522624 diff --git a/controllable-llama2-7b.Q2_K.gguf b/controllable-llama2-7b.Q2_K.gguf new file mode 100644 index 0000000..5df8070 --- /dev/null +++ b/controllable-llama2-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2439bd5cccd93f4f8f53d02fdbbc0a1651974b068e5edaa5f300592182311f69 +size 2532869120 diff --git a/controllable-llama2-7b.Q3_K_L.gguf b/controllable-llama2-7b.Q3_K_L.gguf new file mode 100644 index 0000000..984eff0 --- /dev/null +++ b/controllable-llama2-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e1a75a0add3f20301fb97c8fe64b6275b9755459424adbbe2ef34900d607ba +size 3597116832 diff --git a/controllable-llama2-7b.Q3_K_M.gguf b/controllable-llama2-7b.Q3_K_M.gguf new file mode 100644 index 0000000..cccd8fc --- /dev/null +++ b/controllable-llama2-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4397cbe03fef6532b3799352344b8960cc8882af656cb0941532318ce86e8d28 +size 3298010528 diff --git a/controllable-llama2-7b.Q3_K_S.gguf b/controllable-llama2-7b.Q3_K_S.gguf new file mode 100644 index 0000000..cde470b --- /dev/null +++ b/controllable-llama2-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ffdc8dce4c511addfecaf61b7d99f3379ee9afba1f44c05af0752b06bea5347 +size 2948310432 diff --git a/controllable-llama2-7b.Q4_K_M.gguf b/controllable-llama2-7b.Q4_K_M.gguf new file mode 100644 index 0000000..8d688be --- /dev/null +++ b/controllable-llama2-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a8dfe73fc14ec8708840f63595222dabbf520cad2a44e16ba563c9aef4a7d7d +size 4081010624 diff --git a/controllable-llama2-7b.Q4_K_S.gguf b/controllable-llama2-7b.Q4_K_S.gguf new file mode 100644 index 0000000..bc33643 --- /dev/null +++ b/controllable-llama2-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3665d6ff6ba0ccece76d706b42bfe185232b728455024ad2bfbfc7d81d06d2 +size 3856746432 diff --git a/controllable-llama2-7b.Q5_K_M.gguf b/controllable-llama2-7b.Q5_K_M.gguf new file mode 100644 index 0000000..1a7571c --- /dev/null +++ b/controllable-llama2-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c60c43582d89b4aa82e66474b0b4e348641783a4dba6e3c566e97bc2200737f +size 4783163840 diff --git a/controllable-llama2-7b.Q5_K_S.gguf b/controllable-llama2-7b.Q5_K_S.gguf new file mode 100644 index 0000000..0cb5464 --- /dev/null +++ b/controllable-llama2-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5159ba20e76c08a3711cd9a462550341b877acadeb48f63062bf2ef3c0c09d3 +size 4651698624 diff --git a/controllable-llama2-7b.Q6_K.gguf b/controllable-llama2-7b.Q6_K.gguf new file mode 100644 index 0000000..c055fda --- /dev/null +++ b/controllable-llama2-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad404faf1c61c3b7c2666c9405056d2c5460b4cbc0caf7552070bf12bafe78ea +size 5529201632 diff --git a/controllable-llama2-7b.Q8_0.gguf b/controllable-llama2-7b.Q8_0.gguf new file mode 100644 index 0000000..174f4b9 --- /dev/null +++ b/controllable-llama2-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35693a7d7724ab876eb2e2b812c0d8dec220d17c9e9840430dc99ff61b018350 +size 7161099168 diff --git a/controllable-llama2-7b.f16.gguf b/controllable-llama2-7b.f16.gguf new file mode 100644 index 0000000..d131eb0 --- /dev/null +++ b/controllable-llama2-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a70abee7ee0c224aad20e1a2a1b201c0a4eac6879087506354569cf8b35ee14 +size 13478121888