commit 11953d91dcb87f3e38559fe697e7358546a41ec6 Author: ModelHub XC Date: Thu Jun 18 07:44:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..84ca649 --- /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 +llama3-8b-cpt-sahabatai-v1-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sahabatai-v1-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sahabatai-v1-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sahabatai-v1-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sahabatai-v1-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sahabatai-v1-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sahabatai-v1-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-8b-cpt-sahabatai-v1-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..480f823 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct +language: +- en +- id +- jv +- su +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct + + +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/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-8b-cpt-sahabatai-v1-instruct-GGUF/resolve/main/llama3-8b-cpt-sahabatai-v1-instruct.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/llama3-8b-cpt-sahabatai-v1-instruct.IQ4_XS.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..ee1adbc --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6623fbaeece9fb3095c93876167d8d8c7024e190caf0705266c5359b0aca87b +size 4484363840 diff --git a/llama3-8b-cpt-sahabatai-v1-instruct.Q2_K.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.Q2_K.gguf new file mode 100644 index 0000000..57a470e --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59fe016e616f5603fb5274e6e4fae768db1326c892051f1dd87d9f9489fd7a51 +size 3179132480 diff --git a/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_L.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..2e5b744 --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb4f653d8d0ea8dc9396c07545c44e07b8a371dc47dbc0a72027598a103dbea +size 4321957440 diff --git a/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..3b14de3 --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8d4cb076b9e18e7b349d1832bdddf3565409e7b729aebec27a5c2de75e734f +size 4018918976 diff --git a/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..32f9dae --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5957230b724b56bb9e614d570a00bcf2ef7e0286326cc30c5af092dcd668cc8 +size 3664500288 diff --git a/llama3-8b-cpt-sahabatai-v1-instruct.Q4_K_M.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..d31c559 --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50a8fc7d4fd60ef9f89113cebc03fb41baf2f809e1195592c830a8b03154a9ec +size 4920735296 diff --git a/llama3-8b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..4974942 --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88004f8d58112cce1681f7fd8ea10c3ce2f3eb0f5a502cd4f7bc91747e1e0b23 +size 4692670016 diff --git a/llama3-8b-cpt-sahabatai-v1-instruct.Q5_K_M.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..7766450 --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5214b24ade0da279a541a9d404b956f80f4063422a81a0055bccf35d2f9c2292 +size 5732988480 diff --git a/llama3-8b-cpt-sahabatai-v1-instruct.Q5_K_S.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..c4142c0 --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ef4db10b6aae7c7fc0e13c2821e87badd18233f1c16cc649c7db9ed3848b0f1 +size 5599295040 diff --git a/llama3-8b-cpt-sahabatai-v1-instruct.Q6_K.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.Q6_K.gguf new file mode 100644 index 0000000..6a684e2 --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6044c07773c1c3ecffe9f614b835eb495ff6d12e10a616125ac64c1b81b998fc +size 6596007488 diff --git a/llama3-8b-cpt-sahabatai-v1-instruct.Q8_0.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.Q8_0.gguf new file mode 100644 index 0000000..c465bb8 --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fafe01819a8ddecbc19b41bf391df733f22f85a5c0e83d1e3a01633946b39044 +size 8540771904 diff --git a/llama3-8b-cpt-sahabatai-v1-instruct.f16.gguf b/llama3-8b-cpt-sahabatai-v1-instruct.f16.gguf new file mode 100644 index 0000000..decf5d5 --- /dev/null +++ b/llama3-8b-cpt-sahabatai-v1-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c136fd07d71443c0862a1609cc7179496aa538e3ff32cbe0b1b877e69c58fa +size 16068892224