commit 932e8a17b70e35fdb4876b6e81eba90a726833ec Author: ModelHub XC Date: Tue Jun 2 11:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7d358b5 --- /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 +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_M.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_M.gguf new file mode 100644 index 0000000..f0c4697 --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bfd00390fa20a45a638db8c9bc302fb156cafc64edc71900e00b1acc1aa7390 +size 3784823840 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_S.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_S.gguf new file mode 100644 index 0000000..7d57098 --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a2d44a4993621c731cc1e4ce797c1d347dae2801dff3ceab7496d036d0760fd +size 3682325536 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_XS.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_XS.gguf new file mode 100644 index 0000000..bbd86e6 --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f7de1527cb9e7e461e871d89043adb1b1e22beffc1ad0074718b58665594c1 +size 3518747680 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ4_XS.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..549f69f --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7a584d5e7a79b351c1b70ac37b84f3622b12f288267b1595bcf820e520ddb0 +size 4484363296 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q2_K.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q2_K.gguf new file mode 100644 index 0000000..bf9aa02 --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71498973b1de033c6c7598b8dcdfab85b0ceac189cf96dfdd84a77b3713bc560 +size 3179131936 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_L.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..8eede24 --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5e7d79a3cfb58b12fd38db8ed93a54e2370e36176f9ec38146d040a1f525b1 +size 4321956896 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_M.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..e439599 --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e32e7212d4cd754e28b1ae400ccc316c16ef846c5841cbc89ce0ac8c9400b68 +size 4018918432 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_S.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..3a2284f --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fd9535da0cbaed6c765470ec42fcfaa0798c13b9ff4344c07db8e2ca9ac32b3 +size 3664499744 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q4_K_M.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..c23cc40 --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c1d4792657ea193a67117a91911b12fbf2acfbf2ffffe3f0eaad8fe0e886e1 +size 4920734752 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q4_K_S.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..2b7f59b --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4194d941af51854e5be0a33ef2167512670c743fa50306c487b3b45923e1fdf6 +size 4692669472 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q5_K_M.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..576cc7b --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e63746740ada29e441cb252445c0606a15d5382f5e70e840ca2dfed76057c32 +size 5732987936 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q5_K_S.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..65770da --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdef4fd6f2ae299bfb01ff1161f619c0b299345778462f81126d1083af0e5cfb +size 5599294496 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q6_K.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q6_K.gguf new file mode 100644 index 0000000..3dbae30 --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6564746a2404124ea5749fb8d6a76186fcfcb65ec0b8651a3da181e95d88a1a7 +size 6596006944 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q8_0.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q8_0.gguf new file mode 100644 index 0000000..802c8b3 --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb817a552614086109b4140516c4acc9b9b08319450ca960d13af0fb15db2df0 +size 8540771360 diff --git a/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.f16.gguf b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.f16.gguf new file mode 100644 index 0000000..a31630b --- /dev/null +++ b/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d300dcb046025b4fc145d352548e758d7e5fe0863c1268ed397ccd41d8b11479 +size 16068891680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2d94bfa --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: OwenArli/ArliAI-Llama-3-8B-Instruct-DPO-v0.1 +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Instruct-DPO-v0.1 + + +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/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Awanllm-Llama-3-8B-Instruct-DPO-v0.1-GGUF/resolve/main/Awanllm-Llama-3-8B-Instruct-DPO-v0.1.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. + +