commit 429c371d65bc1d5a897f9452e66d09a4e837b1db Author: ModelHub XC Date: Wed Jul 15 02:02:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Pyg-Llama-8B-1M-0.25-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2be1605 --- /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 +Pyg-Llama-8B-1M-0.25.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pyg-Llama-8B-1M-0.25.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Pyg-Llama-8B-1M-0.25.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pyg-Llama-8B-1M-0.25.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pyg-Llama-8B-1M-0.25.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Pyg-Llama-8B-1M-0.25.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Pyg-Llama-8B-1M-0.25.f16.gguf filter=lfs diff=lfs merge=lfs -text +Pyg-Llama-8B-1M-0.25.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Pyg-Llama-8B-1M-0.25.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pyg-Llama-8B-1M-0.25.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Pyg-Llama-8B-1M-0.25.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Pyg-Llama-8B-1M-0.25.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Pyg-Llama-8B-1M-0.25.IQ4_XS.gguf b/Pyg-Llama-8B-1M-0.25.IQ4_XS.gguf new file mode 100644 index 0000000..9f5e16a --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb805b36a4c4780c7d513671a85cbbc28c9d01ce434bda1ff6780174b85b576 +size 4484391040 diff --git a/Pyg-Llama-8B-1M-0.25.Q2_K.gguf b/Pyg-Llama-8B-1M-0.25.Q2_K.gguf new file mode 100644 index 0000000..d05c8a0 --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda93e26b10801f94efef7f24273e36463265da58b7a155fc632cbb62d006f59 +size 3179155520 diff --git a/Pyg-Llama-8B-1M-0.25.Q3_K_L.gguf b/Pyg-Llama-8B-1M-0.25.Q3_K_L.gguf new file mode 100644 index 0000000..a539a96 --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91eb9d121099655ffcac9d4ac24a85df6f5dc6b5a5915611b1948f366560f588 +size 4321982560 diff --git a/Pyg-Llama-8B-1M-0.25.Q3_K_M.gguf b/Pyg-Llama-8B-1M-0.25.Q3_K_M.gguf new file mode 100644 index 0000000..36718be --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af945251f5a3c6f92065d8bbd8b2ad78372299bd26ba7cb9c7e5864883d5535 +size 4018944096 diff --git a/Pyg-Llama-8B-1M-0.25.Q3_K_S.gguf b/Pyg-Llama-8B-1M-0.25.Q3_K_S.gguf new file mode 100644 index 0000000..b289975 --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3419a713396bcc07e7b0c679eadb5509d6b68cf8076b62d8b50060a073758c04 +size 3664525408 diff --git a/Pyg-Llama-8B-1M-0.25.Q4_K_M.gguf b/Pyg-Llama-8B-1M-0.25.Q4_K_M.gguf new file mode 100644 index 0000000..6e72d16 --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:564c6043498d691d0b63a35fa3303261297939e936669c2730b46795166d7b78 +size 4920763136 diff --git a/Pyg-Llama-8B-1M-0.25.Q4_K_S.gguf b/Pyg-Llama-8B-1M-0.25.Q4_K_S.gguf new file mode 100644 index 0000000..26df623 --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e71b1d6ee4ef1caa89008b4689d545fc8db6cdc4e8c43afe1bb4692631e0a6aa +size 4692697856 diff --git a/Pyg-Llama-8B-1M-0.25.Q5_K_M.gguf b/Pyg-Llama-8B-1M-0.25.Q5_K_M.gguf new file mode 100644 index 0000000..52d81b4 --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc3dc02e86b9158c214e91b56e26e9aa7c2db83040248b1ca1884a5e6779627e +size 5733018880 diff --git a/Pyg-Llama-8B-1M-0.25.Q5_K_S.gguf b/Pyg-Llama-8B-1M-0.25.Q5_K_S.gguf new file mode 100644 index 0000000..61805ef --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f4a75afd85934f187e4f06e940362b9057c16772900c6d42bcef3f1abbe9324 +size 5599325440 diff --git a/Pyg-Llama-8B-1M-0.25.Q6_K.gguf b/Pyg-Llama-8B-1M-0.25.Q6_K.gguf new file mode 100644 index 0000000..abd3bb3 --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc0f6f8874ccec4974997faa5751b585a786a48d9654347e454f53576d42f039 +size 6596040608 diff --git a/Pyg-Llama-8B-1M-0.25.Q8_0.gguf b/Pyg-Llama-8B-1M-0.25.Q8_0.gguf new file mode 100644 index 0000000..02d7f6f --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8090c17346206c577173f10ddf3372786b7c62813529744b0d170b73f358572 +size 8540814944 diff --git a/Pyg-Llama-8B-1M-0.25.f16.gguf b/Pyg-Llama-8B-1M-0.25.f16.gguf new file mode 100644 index 0000000..7bf78b0 --- /dev/null +++ b/Pyg-Llama-8B-1M-0.25.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6293e9d9ca3d3380a75d2b925fb6658ff156f338aff0c1c81005d36a1d8a4370 +size 16068973664 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ae136af --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: tavtav/Pyg-Llama-8B-1M-0.25 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/tavtav/Pyg-Llama-8B-1M-0.25 + + +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/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Pyg-Llama-8B-1M-0.25-GGUF/resolve/main/Pyg-Llama-8B-1M-0.25.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. + +