commit 51ec194fcf877686cc190653e6fb7327a4f6654f Author: ModelHub XC Date: Wed Apr 15 20:43:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5f1d0b2 --- /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 +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-3-8B-openassistant-guanaco-llama2-format.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_M.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_M.gguf new file mode 100644 index 0000000..7dcd74e --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70f1f6571e37a1841dd482b22cf2aa9317f670f8a05f200400427bf05889e058 +size 3784823776 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_S.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_S.gguf new file mode 100644 index 0000000..860b388 --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2d528ec6842ba6dcbebd41a9e258ffbb6afb999606aeaef37d49eb31e43fb19 +size 3682325472 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_XS.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_XS.gguf new file mode 100644 index 0000000..01877a6 --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b443988eb7ccfd97d9c2339f5ed2b9307f41a554d83e8897a703fe724774f9bc +size 3518747616 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ4_XS.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ4_XS.gguf new file mode 100644 index 0000000..df26d07 --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f2cc10d9082178ec857bbb715cc7f03dd0efa40e6ae90a71e1206d594ce34f9 +size 4484363232 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q2_K.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q2_K.gguf new file mode 100644 index 0000000..4a227f3 --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bc927e87234760f40ab42d20cabc365a14d426daf75910377bab6d18f474017 +size 3179131872 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_L.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_L.gguf new file mode 100644 index 0000000..28686db --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eb26ab19a09cfdc462871e7d77e8b2c5eae4121a3a75d0c02e49951be44c715 +size 4321956832 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_M.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_M.gguf new file mode 100644 index 0000000..ffb63db --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21f5662ad52fcf32f5af05246552e640461f0dea152600f96cc5cccad24d1aee +size 4018918368 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_S.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_S.gguf new file mode 100644 index 0000000..7c59bbe --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7bd05be267a6891df64b32619042e438d76ab2b67549e7562e4fe9f156dd69c +size 3664499680 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q4_K_M.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q4_K_M.gguf new file mode 100644 index 0000000..58cf54a --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0612bd04ac0ad5f4634680de4b5fa3a34584e9a8528e9cb07e7013fae63bcf9 +size 4920734688 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q4_K_S.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q4_K_S.gguf new file mode 100644 index 0000000..79cf374 --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4172249dfd5539e789072920b88dc076e8f5218498a027a380c57a00fa599c21 +size 4692669408 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q5_K_M.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q5_K_M.gguf new file mode 100644 index 0000000..614fbce --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7747539617db55d4b273f1e88187eb618fd46f053e95215e877dd9f997e066bf +size 5732987872 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q5_K_S.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q5_K_S.gguf new file mode 100644 index 0000000..82006aa --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adeb3462d232bed865ad8ebb7bb7067d62442e287ed09b90915f402eb952ba69 +size 5599294432 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q6_K.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q6_K.gguf new file mode 100644 index 0000000..1384e9e --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9118139216178cc0657b64969fc860a831aedddefc50d566dc5fe6b2265d9d1 +size 6596006880 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q8_0.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q8_0.gguf new file mode 100644 index 0000000..c2c0dab --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b98f35843c86ae335d82c8696882e7222fab98c10ec8ce98371ab971ff37738e +size 8540771296 diff --git a/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.f16.gguf b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.f16.gguf new file mode 100644 index 0000000..b6558a8 --- /dev/null +++ b/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551504ddc88f87ec0afdbead4751e6000f50cb977f1e056f1dfbfff7cbedf66a +size 16068891616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..078beac --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: gpjt/Meta-Llama-3-8B-openassistant-guanaco-llama2-format +datasets: +- gpjt/openassistant-guanaco-llama2-format +language: +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/gpjt/Meta-Llama-3-8B-openassistant-guanaco-llama2-format + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-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/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-openassistant-guanaco-llama2-format-GGUF/resolve/main/Meta-Llama-3-8B-openassistant-guanaco-llama2-format.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. + +