commit b92edf1bac4142d7ffc670c46b9b104b5b8ee087 Author: ModelHub XC Date: Wed Oct 7 08:23:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Meta-Llama-G1-OS-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..51aa1a0 --- /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 +Meta-Llama-G1-OS.f16.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-G1-OS.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-G1-OS.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-G1-OS.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-G1-OS.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-G1-OS.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-G1-OS.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-G1-OS.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-G1-OS.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-G1-OS.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-G1-OS.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Meta-Llama-G1-OS.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-G1-OS.IQ4_XS.gguf b/Meta-Llama-G1-OS.IQ4_XS.gguf new file mode 100644 index 0000000..9fb1de5 --- /dev/null +++ b/Meta-Llama-G1-OS.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96b7c82ddac58dffdae65df9ba472da4049fb544ebd68583b81c4a0aa7269728 +size 4484362880 diff --git a/Meta-Llama-G1-OS.Q2_K.gguf b/Meta-Llama-G1-OS.Q2_K.gguf new file mode 100644 index 0000000..0fbe1ba --- /dev/null +++ b/Meta-Llama-G1-OS.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b1fca6c40f4aa70ef3101f8a0402952f7519eb08929ffcd6fb1740b06ad49a +size 3179131520 diff --git a/Meta-Llama-G1-OS.Q3_K_L.gguf b/Meta-Llama-G1-OS.Q3_K_L.gguf new file mode 100644 index 0000000..ca808e6 --- /dev/null +++ b/Meta-Llama-G1-OS.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0aa50af75888e9567c1ad7cc883c83ec8e69fa87c49ba721528767f2270c485 +size 4321956480 diff --git a/Meta-Llama-G1-OS.Q3_K_M.gguf b/Meta-Llama-G1-OS.Q3_K_M.gguf new file mode 100644 index 0000000..c57ac7a --- /dev/null +++ b/Meta-Llama-G1-OS.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2d84c96160040a4e0e0bfe68cf5ef2e6151fe0678631d3fb61873c6657b629 +size 4018918016 diff --git a/Meta-Llama-G1-OS.Q3_K_S.gguf b/Meta-Llama-G1-OS.Q3_K_S.gguf new file mode 100644 index 0000000..afd41cf --- /dev/null +++ b/Meta-Llama-G1-OS.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b6bfb536e3081ba1a151dad035bb240c9075a5ac49ff918445268214ac68867 +size 3664499328 diff --git a/Meta-Llama-G1-OS.Q4_K_M.gguf b/Meta-Llama-G1-OS.Q4_K_M.gguf new file mode 100644 index 0000000..c0425c7 --- /dev/null +++ b/Meta-Llama-G1-OS.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8ba244ef7dc5c35dee62eb91deadd988a6be7d5bdce6a42ad5cd5f80dbb01f8 +size 4920734336 diff --git a/Meta-Llama-G1-OS.Q4_K_S.gguf b/Meta-Llama-G1-OS.Q4_K_S.gguf new file mode 100644 index 0000000..6761126 --- /dev/null +++ b/Meta-Llama-G1-OS.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6e31aa559795031ee2941457c56b7f4ceaa25d8fa4fd6c9483d7dd2d59b95a8 +size 4692669056 diff --git a/Meta-Llama-G1-OS.Q5_K_M.gguf b/Meta-Llama-G1-OS.Q5_K_M.gguf new file mode 100644 index 0000000..04d3998 --- /dev/null +++ b/Meta-Llama-G1-OS.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f6038fd1a2f071c177e2467a4f511aea7e8ef61c028938741574edae7dfa14d +size 5732987520 diff --git a/Meta-Llama-G1-OS.Q5_K_S.gguf b/Meta-Llama-G1-OS.Q5_K_S.gguf new file mode 100644 index 0000000..562c032 --- /dev/null +++ b/Meta-Llama-G1-OS.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e76ec2be3f11f330ff23291e6d033d2dccba3b0f133fbdd8668206425fb2f27b +size 5599294080 diff --git a/Meta-Llama-G1-OS.Q6_K.gguf b/Meta-Llama-G1-OS.Q6_K.gguf new file mode 100644 index 0000000..426dea8 --- /dev/null +++ b/Meta-Llama-G1-OS.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:995faa4f929c9ccaf78771647c3140ac83dd3980919ae6776112a3ee7fb00eee +size 6596006528 diff --git a/Meta-Llama-G1-OS.Q8_0.gguf b/Meta-Llama-G1-OS.Q8_0.gguf new file mode 100644 index 0000000..88dde65 --- /dev/null +++ b/Meta-Llama-G1-OS.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98880a6b2c778fd05afc864ae2602d5bf54d54ffb707f4dadc910906a96934ad +size 8540770944 diff --git a/Meta-Llama-G1-OS.f16.gguf b/Meta-Llama-G1-OS.f16.gguf new file mode 100644 index 0000000..c4791a8 --- /dev/null +++ b/Meta-Llama-G1-OS.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb2e348bbedefdc19e69434d564a8b5c8fc3e041dc7e48b6ba8610ac385c77e2 +size 16068891264 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9c83c4a --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Piyush47890/Meta-Llama-G1-OS +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Piyush47890/Meta-Llama-G1-OS + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Meta-Llama-G1-OS-GGUF).*** + +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/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Meta-Llama-G1-OS-GGUF/resolve/main/Meta-Llama-G1-OS.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. + +