commit b8881bab2ae73d129bbf295ba92ee5117a5d8bb1 Author: ModelHub XC Date: Sun Oct 4 04:55:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LlamaPhilosopher-1.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fea6dd9 --- /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 +LlamaPhilosopher-1.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaPhilosopher-1.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LlamaPhilosopher-1.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +LlamaPhilosopher-1.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaPhilosopher-1.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaPhilosopher-1.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaPhilosopher-1.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaPhilosopher-1.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LlamaPhilosopher-1.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LlamaPhilosopher-1.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LlamaPhilosopher-1.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LlamaPhilosopher-1.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LlamaPhilosopher-1.1-8B.IQ4_XS.gguf b/LlamaPhilosopher-1.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..68e2e6e --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e267d7f2128c1974bbfb74e8868d3e6cf6f595a509c1b7ed63b94ebdc21c1288 +size 4484368288 diff --git a/LlamaPhilosopher-1.1-8B.Q2_K.gguf b/LlamaPhilosopher-1.1-8B.Q2_K.gguf new file mode 100644 index 0000000..49bed07 --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25521b80ba64d74dda5f613b92c58a93b832b294b2c7bf4023748c6ff0728770 +size 3179136928 diff --git a/LlamaPhilosopher-1.1-8B.Q3_K_L.gguf b/LlamaPhilosopher-1.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..de9d800 --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0470cf8a6ef0d5bda0474b2af689eecf72fb49170c7583365539b1fdae37abc7 +size 4321961888 diff --git a/LlamaPhilosopher-1.1-8B.Q3_K_M.gguf b/LlamaPhilosopher-1.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..b239a31 --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2fd448192138d99a3fed7123f0dc7fd94e49815df26dc9e07f04a11a8d35696 +size 4018923424 diff --git a/LlamaPhilosopher-1.1-8B.Q3_K_S.gguf b/LlamaPhilosopher-1.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..6821dd4 --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccea4ae6722b2173ea52db5916fe553c46553635f4b6fc864471eceb9ea67fb3 +size 3664504736 diff --git a/LlamaPhilosopher-1.1-8B.Q4_K_M.gguf b/LlamaPhilosopher-1.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..a629dc3 --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2847626f13556793015bc492fd074cf5b77ee7b7bb337ab7b189ae2bba5e7c67 +size 4920739744 diff --git a/LlamaPhilosopher-1.1-8B.Q4_K_S.gguf b/LlamaPhilosopher-1.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..7104e5a --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827dc92bea5bf7cd6698d4609ecc00c9d339d81c9d2417222c617f650bea6fa0 +size 4692674464 diff --git a/LlamaPhilosopher-1.1-8B.Q5_K_M.gguf b/LlamaPhilosopher-1.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..46a7482 --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384e8b30e83e16dac1b41973273d7be320ede01458a168086fdc37ba9a557633 +size 5732992928 diff --git a/LlamaPhilosopher-1.1-8B.Q5_K_S.gguf b/LlamaPhilosopher-1.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..fcb3bc8 --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:339e3017ea86e24d033b15adf8f3ef4ed9733480d2f825974658589c5d84ee75 +size 5599299488 diff --git a/LlamaPhilosopher-1.1-8B.Q6_K.gguf b/LlamaPhilosopher-1.1-8B.Q6_K.gguf new file mode 100644 index 0000000..225f2cc --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edb96b7d2dff4060094ae54ed2ef285aa20ee9979a4add2435f955e1b7fd1cfc +size 6596011936 diff --git a/LlamaPhilosopher-1.1-8B.Q8_0.gguf b/LlamaPhilosopher-1.1-8B.Q8_0.gguf new file mode 100644 index 0000000..57f92ad --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c48ca526af039db92e61132731546b7041abec829c3301000799f374b3152fa +size 8540776352 diff --git a/LlamaPhilosopher-1.1-8B.f16.gguf b/LlamaPhilosopher-1.1-8B.f16.gguf new file mode 100644 index 0000000..26b7406 --- /dev/null +++ b/LlamaPhilosopher-1.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af25baef2dc460fabc25c8f9c808d42abfc6fe573afacb5064e9018f57e8997a +size 16068896672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8f97901 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: oscar128372/LlamaPhilosopher-1.1-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/oscar128372/LlamaPhilosopher-1.1-8B + + +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/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LlamaPhilosopher-1.1-8B-GGUF/resolve/main/LlamaPhilosopher-1.1-8B.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. + +