commit 3024ad7b95d8187cb2e250601c6f099c94404bfe Author: ModelHub XC Date: Sun Apr 26 13:17:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1fd1d09 --- /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 +TruthRL-Llama-3.1-8B-Instruct-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +TruthRL-Llama-3.1-8B-Instruct-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TruthRL-Llama-3.1-8B-Instruct-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TruthRL-Llama-3.1-8B-Instruct-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TruthRL-Llama-3.1-8B-Instruct-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TruthRL-Llama-3.1-8B-Instruct-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TruthRL-Llama-3.1-8B-Instruct-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TruthRL-Llama-3.1-8B-Instruct-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TruthRL-Llama-3.1-8B-Instruct-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8b75306 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: muyu0515/TruthRL-Llama-3.1-8B-Instruct-GRPO +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/muyu0515/TruthRL-Llama-3.1-8B-Instruct-GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TruthRL-Llama-3.1-8B-Instruct-GRPO-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/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TruthRL-Llama-3.1-8B-Instruct-GRPO-GGUF/resolve/main/TruthRL-Llama-3.1-8B-Instruct-GRPO.f16.gguf) | f16 | 16.2 | 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/TruthRL-Llama-3.1-8B-Instruct-GRPO.IQ4_XS.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..6701b64 --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44f46f57a92ea48285192d5899e96fd04b58a1637a7d8c04b466106ace6338f +size 4484367968 diff --git a/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q2_K.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q2_K.gguf new file mode 100644 index 0000000..73d3219 --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285ee8e1af482d716a3055aeaa97c5e8ca052faaff0911ad2408134ba042411a +size 3179136608 diff --git a/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_L.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..1329a43 --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f75fe283d62375cdc96bb6f1364fc3415611452a18ce616a43ebae3b75f2cbac +size 4321961568 diff --git a/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_M.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..55cd525 --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d748b7038afeb3a35025930504ded74ac761da558f3ac5444dfa870825c33b6 +size 4018923104 diff --git a/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_S.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..b82984a --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e7b614f3d2a49ed2ae5d5ea9d9306546189c03e4dec8d86669f261a9e4406cf +size 3664504416 diff --git a/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q4_K_M.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..92e2bd3 --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bac4c018b2300ab6712b2885494a49b91d1b45a1a7f3726237de00d55f810cd +size 4920739424 diff --git a/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q4_K_S.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..a705b83 --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17bc9f44cf059f7edd0533434c36135841437ed783228b6be11149d6fceb6b28 +size 4692674144 diff --git a/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q5_K_M.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..45f2d8a --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70c51fd35b4dcaf3da101b679c7fbdd9e85f2974ca1d87d62f511f65543f32dc +size 5732992608 diff --git a/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q5_K_S.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..b2ea86a --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e9b5b2ab531cb7ca63a00f32dd1f3302eaea94a8c6ea97e17576399aae3b61 +size 5599299168 diff --git a/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q6_K.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q6_K.gguf new file mode 100644 index 0000000..e73f117 --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f85196aa35eebf782572cac2faf98fad7d0b266d54fa39a97e3ab9fe1193f6 +size 6596011616 diff --git a/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q8_0.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q8_0.gguf new file mode 100644 index 0000000..62b9812 --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a34873d4c7202c34a3afe9e948a55924311d84b5e931211546a1d453d995ab3 +size 8540776032 diff --git a/TruthRL-Llama-3.1-8B-Instruct-GRPO.f16.gguf b/TruthRL-Llama-3.1-8B-Instruct-GRPO.f16.gguf new file mode 100644 index 0000000..3fb8b7c --- /dev/null +++ b/TruthRL-Llama-3.1-8B-Instruct-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66bde1f15ef9da0f2f8521c9c137e7f2df3379fbf8d7213f70cc1b098f80fb7c +size 16068896352