commit 3f118ec8465a4a9b93df9bd9f12ad46b4ea5ee5e Author: ModelHub XC Date: Thu Jun 18 03:14:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-Nephilim-v2-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8338959 --- /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 +llama-3-Nephilim-v2-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-Nephilim-v2-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b5e0509 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: grimjim/llama-3-Nephilim-v2-8B +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/grimjim/llama-3-Nephilim-v2-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-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-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-Nephilim-v2-8B-GGUF/resolve/main/llama-3-Nephilim-v2-8B.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/llama-3-Nephilim-v2-8B.IQ3_M.gguf b/llama-3-Nephilim-v2-8B.IQ3_M.gguf new file mode 100644 index 0000000..84a6dcd --- /dev/null +++ b/llama-3-Nephilim-v2-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:701ede87bb9ddeef9a294b23c16fd2c39e956f5418214e755047d97344bcec08 +size 3784823520 diff --git a/llama-3-Nephilim-v2-8B.IQ3_S.gguf b/llama-3-Nephilim-v2-8B.IQ3_S.gguf new file mode 100644 index 0000000..c809d86 --- /dev/null +++ b/llama-3-Nephilim-v2-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8e0765acb536ed31526467ab83868f796409bcef05143fbd65dfcba01168f2 +size 3682325216 diff --git a/llama-3-Nephilim-v2-8B.IQ3_XS.gguf b/llama-3-Nephilim-v2-8B.IQ3_XS.gguf new file mode 100644 index 0000000..6f726d0 --- /dev/null +++ b/llama-3-Nephilim-v2-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:351e6f54c3837423342a31ad5b483c69c754bcd39f180edfedea314b9af35e78 +size 3518747360 diff --git a/llama-3-Nephilim-v2-8B.IQ4_XS.gguf b/llama-3-Nephilim-v2-8B.IQ4_XS.gguf new file mode 100644 index 0000000..07b518f --- /dev/null +++ b/llama-3-Nephilim-v2-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:978495d3a5d36973ae607e4383f6a3e7d5beecfacbb8642272f4c0bc94a49ac0 +size 4484362976 diff --git a/llama-3-Nephilim-v2-8B.Q2_K.gguf b/llama-3-Nephilim-v2-8B.Q2_K.gguf new file mode 100644 index 0000000..e1789c9 --- /dev/null +++ b/llama-3-Nephilim-v2-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22c817795d68a834ad34792ead26a94d787a3ef233326e17da80649bc44d4ff +size 3179131616 diff --git a/llama-3-Nephilim-v2-8B.Q3_K_L.gguf b/llama-3-Nephilim-v2-8B.Q3_K_L.gguf new file mode 100644 index 0000000..f39f3f1 --- /dev/null +++ b/llama-3-Nephilim-v2-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f0c5d235aff4d4c8bed10807044ac3748411398bbc8a355eaafe17fc02c1fd1 +size 4321956576 diff --git a/llama-3-Nephilim-v2-8B.Q3_K_M.gguf b/llama-3-Nephilim-v2-8B.Q3_K_M.gguf new file mode 100644 index 0000000..3fcfa44 --- /dev/null +++ b/llama-3-Nephilim-v2-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee736656d0c52da5a66c4992137a096f827e5659950fd2a5205a613af3e972d3 +size 4018918112 diff --git a/llama-3-Nephilim-v2-8B.Q3_K_S.gguf b/llama-3-Nephilim-v2-8B.Q3_K_S.gguf new file mode 100644 index 0000000..ee41cce --- /dev/null +++ b/llama-3-Nephilim-v2-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98123a4da40cffc7768bd442a1d4b459a57152c75dd018dfcef5f638475390b8 +size 3664499424 diff --git a/llama-3-Nephilim-v2-8B.Q4_K_M.gguf b/llama-3-Nephilim-v2-8B.Q4_K_M.gguf new file mode 100644 index 0000000..447ac6c --- /dev/null +++ b/llama-3-Nephilim-v2-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d81e0d39715fb7c909c64166c7f2ed88718ac921bf895b726696c2b4f93debc +size 4920734432 diff --git a/llama-3-Nephilim-v2-8B.Q4_K_S.gguf b/llama-3-Nephilim-v2-8B.Q4_K_S.gguf new file mode 100644 index 0000000..677cc00 --- /dev/null +++ b/llama-3-Nephilim-v2-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:622a622ea4fbb6620258a0813947f58f4cf92aeb6738d30a78c157558589bbbe +size 4692669152 diff --git a/llama-3-Nephilim-v2-8B.Q5_K_M.gguf b/llama-3-Nephilim-v2-8B.Q5_K_M.gguf new file mode 100644 index 0000000..0d99bf5 --- /dev/null +++ b/llama-3-Nephilim-v2-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c04036fc7e0d665a979aa3a42bd4efb09a56da938b853fc7ce59a85610469dec +size 5732987616 diff --git a/llama-3-Nephilim-v2-8B.Q5_K_S.gguf b/llama-3-Nephilim-v2-8B.Q5_K_S.gguf new file mode 100644 index 0000000..7042db4 --- /dev/null +++ b/llama-3-Nephilim-v2-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6431868f251a83d7859eb795f427c06ec93c9df745aa3172ca7856a9b6f0f81 +size 5599294176 diff --git a/llama-3-Nephilim-v2-8B.Q6_K.gguf b/llama-3-Nephilim-v2-8B.Q6_K.gguf new file mode 100644 index 0000000..a12b28f --- /dev/null +++ b/llama-3-Nephilim-v2-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbf4c9e3a3491086c0119942f8196759a715541ddfd280f713c83f6565f229fc +size 6596006624 diff --git a/llama-3-Nephilim-v2-8B.Q8_0.gguf b/llama-3-Nephilim-v2-8B.Q8_0.gguf new file mode 100644 index 0000000..37defb8 --- /dev/null +++ b/llama-3-Nephilim-v2-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ec4d6078b3851a525069190f2edee484859f25691ce6c7fea606fa1de5eaae0 +size 8540771040 diff --git a/llama-3-Nephilim-v2-8B.f16.gguf b/llama-3-Nephilim-v2-8B.f16.gguf new file mode 100644 index 0000000..9232de4 --- /dev/null +++ b/llama-3-Nephilim-v2-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17854d33b301fc08671dc792e3e3c4c648907ba2ff3409b15bff1f84464d1f08 +size 16068891360