commit b74de65aa9f7e55fa455bf1ae9ae512a4eeec357 Author: ModelHub XC Date: Sat Jun 27 01:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8af3f71 --- /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 +Llama_3.x_8b_Smarteaz_0.1a.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.x_8b_Smarteaz_0.1a.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.x_8b_Smarteaz_0.1a.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.x_8b_Smarteaz_0.1a.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.x_8b_Smarteaz_0.1a.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.x_8b_Smarteaz_0.1a.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.x_8b_Smarteaz_0.1a.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.x_8b_Smarteaz_0.1a.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.x_8b_Smarteaz_0.1a.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.x_8b_Smarteaz_0.1a.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.x_8b_Smarteaz_0.1a.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.x_8b_Smarteaz_0.1a.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.x_8b_Smarteaz_0.1a.IQ4_XS.gguf b/Llama_3.x_8b_Smarteaz_0.1a.IQ4_XS.gguf new file mode 100644 index 0000000..beae58d --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f88e17560995463c67a06177ff469dd3a3e77714e936c6c194b4c528e0eceeb1 +size 4484368768 diff --git a/Llama_3.x_8b_Smarteaz_0.1a.Q2_K.gguf b/Llama_3.x_8b_Smarteaz_0.1a.Q2_K.gguf new file mode 100644 index 0000000..2984be4 --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e80ed65866508e3bbe97ea707078d887b7f5d01abb55363dd68a5a99fb30d09 +size 3179137408 diff --git a/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_L.gguf b/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_L.gguf new file mode 100644 index 0000000..3e7098e --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:488ef1ba7298cfd219b1ae5ec7edec156d0bd5b34d2f38410771330bed4767d8 +size 4321962368 diff --git a/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_M.gguf b/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_M.gguf new file mode 100644 index 0000000..75f80ef --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cff6c739f27e1e2b18e6659c6a0724e55fc636a97a0e5e7c795e9894993c4591 +size 4018923904 diff --git a/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_S.gguf b/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_S.gguf new file mode 100644 index 0000000..26b22eb --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8bf1ef9029536d03d1ddf9e17610da0b2a69eea942b5632438b40900a7a64f +size 3664505216 diff --git a/Llama_3.x_8b_Smarteaz_0.1a.Q4_K_M.gguf b/Llama_3.x_8b_Smarteaz_0.1a.Q4_K_M.gguf new file mode 100644 index 0000000..57b1f7c --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99bfb0ee2479abbe2799888ef51b055e3b9bc24f992a1454ddf3dfb529b2c283 +size 4920740224 diff --git a/Llama_3.x_8b_Smarteaz_0.1a.Q4_K_S.gguf b/Llama_3.x_8b_Smarteaz_0.1a.Q4_K_S.gguf new file mode 100644 index 0000000..dfd0a75 --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2975be3040c7d1d35236cf1b579967269743c3e438d753c3225b34276d3417d1 +size 4692674944 diff --git a/Llama_3.x_8b_Smarteaz_0.1a.Q5_K_M.gguf b/Llama_3.x_8b_Smarteaz_0.1a.Q5_K_M.gguf new file mode 100644 index 0000000..7b1dd62 --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec9e02a7dbeef2e2292612a831b95ff47e631065af3eb4c5d5cf1eb0ebb72a9a +size 5732993408 diff --git a/Llama_3.x_8b_Smarteaz_0.1a.Q5_K_S.gguf b/Llama_3.x_8b_Smarteaz_0.1a.Q5_K_S.gguf new file mode 100644 index 0000000..37a4a5a --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4310879dd1029f3d64d132674755e611df9beca7b1bb40d6b57e1fd2ef7c906f +size 5599299968 diff --git a/Llama_3.x_8b_Smarteaz_0.1a.Q6_K.gguf b/Llama_3.x_8b_Smarteaz_0.1a.Q6_K.gguf new file mode 100644 index 0000000..15a3ad2 --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d5eca63665fdab411e44df056a98d8315206ee5e10414d68a96c94ef955c55 +size 6596012416 diff --git a/Llama_3.x_8b_Smarteaz_0.1a.Q8_0.gguf b/Llama_3.x_8b_Smarteaz_0.1a.Q8_0.gguf new file mode 100644 index 0000000..9456055 --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c064fb1e50bb75024ad0ebfbefb58d22b5f702b1502ce569a0bf033926358a4c +size 8540776832 diff --git a/Llama_3.x_8b_Smarteaz_0.1a.f16.gguf b/Llama_3.x_8b_Smarteaz_0.1a.f16.gguf new file mode 100644 index 0000000..79618fb --- /dev/null +++ b/Llama_3.x_8b_Smarteaz_0.1a.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:697312096f242f9f3331efc3f2cc85a7dd7068d8231c835f213eacf04fd9e365 +size 16068897152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fd1f0b6 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Nexesenex/Llama_3.x_8b_Smarteaz_0.1a +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/Llama_3.x_8b_Smarteaz_0.1a + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-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/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.x_8b_Smarteaz_0.1a-GGUF/resolve/main/Llama_3.x_8b_Smarteaz_0.1a.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. + +