commit ad0ed4ce0ada75454cc4405617068d1f7ff82322 Author: ModelHub XC Date: Sun May 24 19:16:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c7aab62 --- /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-3-8B-ProLong-512k-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ProLong-512k-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ProLong-512k-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ProLong-512k-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ProLong-512k-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ProLong-512k-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ProLong-512k-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ProLong-512k-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ProLong-512k-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ProLong-512k-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ProLong-512k-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-ProLong-512k-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-ProLong-512k-Base.IQ4_XS.gguf b/Llama-3-8B-ProLong-512k-Base.IQ4_XS.gguf new file mode 100644 index 0000000..9766ccd --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d15b3d5ea2e349f05fb19cd0b05ee55522e63a5a2e9ee21c0fa35e75067446 +size 4484364096 diff --git a/Llama-3-8B-ProLong-512k-Base.Q2_K.gguf b/Llama-3-8B-ProLong-512k-Base.Q2_K.gguf new file mode 100644 index 0000000..ed52431 --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be67b28b6c238dfd8b39d68a7ed2cd32453da0c81ac3b3f8aa1bd0370e76dbbf +size 3179132736 diff --git a/Llama-3-8B-ProLong-512k-Base.Q3_K_L.gguf b/Llama-3-8B-ProLong-512k-Base.Q3_K_L.gguf new file mode 100644 index 0000000..47aea75 --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93c7b9208ed9377b932827e8913281d4c9d522b0cc487ae250d392e643c41809 +size 4321957696 diff --git a/Llama-3-8B-ProLong-512k-Base.Q3_K_M.gguf b/Llama-3-8B-ProLong-512k-Base.Q3_K_M.gguf new file mode 100644 index 0000000..1b5f77b --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:794701366be67440518e5803dea112ee1c42b9ff27a9b1187d9dd66bc03be130 +size 4018919232 diff --git a/Llama-3-8B-ProLong-512k-Base.Q3_K_S.gguf b/Llama-3-8B-ProLong-512k-Base.Q3_K_S.gguf new file mode 100644 index 0000000..a4bc0fb --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c38bd2ecbb89fe5b6aa18d986f5424c4c1361110729870123dc8e4d0871c0c44 +size 3664500544 diff --git a/Llama-3-8B-ProLong-512k-Base.Q4_K_M.gguf b/Llama-3-8B-ProLong-512k-Base.Q4_K_M.gguf new file mode 100644 index 0000000..b4bfff9 --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dea832426e3ca927cec703d05494d793934091b44fa7756f34b46e276d002ce +size 4920735552 diff --git a/Llama-3-8B-ProLong-512k-Base.Q4_K_S.gguf b/Llama-3-8B-ProLong-512k-Base.Q4_K_S.gguf new file mode 100644 index 0000000..6fd60b2 --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86233f135ce6a89adf62247fd35a9f1fe1d21f0cf2fe097f6c69462f29d2e50a +size 4692670272 diff --git a/Llama-3-8B-ProLong-512k-Base.Q5_K_M.gguf b/Llama-3-8B-ProLong-512k-Base.Q5_K_M.gguf new file mode 100644 index 0000000..171e307 --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b82def9a6ef3ef16d3afe63f7588bb3d91635e540ca1c5202cbbcf3a1b07f642 +size 5732988736 diff --git a/Llama-3-8B-ProLong-512k-Base.Q5_K_S.gguf b/Llama-3-8B-ProLong-512k-Base.Q5_K_S.gguf new file mode 100644 index 0000000..6533b2f --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4467f7a7686813c6398cecfe1345247e1d527be0a1377f0fa3016b4b74ee82 +size 5599295296 diff --git a/Llama-3-8B-ProLong-512k-Base.Q6_K.gguf b/Llama-3-8B-ProLong-512k-Base.Q6_K.gguf new file mode 100644 index 0000000..ee7df0d --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ca0b2bf2908e8ad98df79f6423a66a10e64ad3f1ba7313b99982b45d53bb6e +size 6596007744 diff --git a/Llama-3-8B-ProLong-512k-Base.Q8_0.gguf b/Llama-3-8B-ProLong-512k-Base.Q8_0.gguf new file mode 100644 index 0000000..5340a61 --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:094a3fa5660cd8f75b68d28579e589763a0747f61eb93965ef53784bc2113f5b +size 8540772160 diff --git a/Llama-3-8B-ProLong-512k-Base.f16.gguf b/Llama-3-8B-ProLong-512k-Base.f16.gguf new file mode 100644 index 0000000..6eb07e0 --- /dev/null +++ b/Llama-3-8B-ProLong-512k-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a6288a71ea86982805ee715a2372cc9b58477a1a1088af89c8328c28e4b6f9e +size 16068892480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9618226 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: princeton-nlp/Llama-3-8B-ProLong-512k-Base +datasets: +- princeton-nlp/prolong-data-64K +- princeton-nlp/prolong-data-512K +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/princeton-nlp/Llama-3-8B-ProLong-512k-Base + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-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-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-ProLong-512k-Base-GGUF/resolve/main/Llama-3-8B-ProLong-512k-Base.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. + +