commit 4ff8980a11ef52930114605f042c5c89fda2027a Author: ModelHub XC Date: Thu Jun 11 07:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Julian-600M-40B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..662427b --- /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 +Julian-600M-40B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Julian-600M-40B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Julian-600M-40B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Julian-600M-40B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Julian-600M-40B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Julian-600M-40B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Julian-600M-40B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Julian-600M-40B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Julian-600M-40B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Julian-600M-40B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Julian-600M-40B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Julian-600M-40B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Julian-600M-40B.IQ4_XS.gguf b/Julian-600M-40B.IQ4_XS.gguf new file mode 100644 index 0000000..1373675 --- /dev/null +++ b/Julian-600M-40B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70e4edd95f6f037508353b3013bd5038f35614a79ffa91bb5cfff2df3b1c400f +size 340511136 diff --git a/Julian-600M-40B.Q2_K.gguf b/Julian-600M-40B.Q2_K.gguf new file mode 100644 index 0000000..c8315ef --- /dev/null +++ b/Julian-600M-40B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03d9e0fbf704f3bda4e93ccc202c33f8a7ebc40f503918d1af1b243eb0cdc74d +size 247587936 diff --git a/Julian-600M-40B.Q3_K_L.gguf b/Julian-600M-40B.Q3_K_L.gguf new file mode 100644 index 0000000..59e5e8e --- /dev/null +++ b/Julian-600M-40B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dfde57dd3da81813b421be33f26a47d1e4df633bc7062efe14fa4e1f4b5f1df +size 329659136 diff --git a/Julian-600M-40B.Q3_K_M.gguf b/Julian-600M-40B.Q3_K_M.gguf new file mode 100644 index 0000000..d1f3aab --- /dev/null +++ b/Julian-600M-40B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e160841819f14283e821ecefd117d5c40f1c0bfc72fb741714f85a5ef7d4193e +size 308769536 diff --git a/Julian-600M-40B.Q3_K_S.gguf b/Julian-600M-40B.Q3_K_S.gguf new file mode 100644 index 0000000..687fbcc --- /dev/null +++ b/Julian-600M-40B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec8b381e68ad8b6775a9da0af119167635fc224458ef19e95309ab118183207c +size 284039936 diff --git a/Julian-600M-40B.Q4_K_M.gguf b/Julian-600M-40B.Q4_K_M.gguf new file mode 100644 index 0000000..933fefe --- /dev/null +++ b/Julian-600M-40B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1d9eb6e082a83004ff68714ca69e20c2700aef0d139c7cfa6cf71dad858c785 +size 374216736 diff --git a/Julian-600M-40B.Q4_K_S.gguf b/Julian-600M-40B.Q4_K_S.gguf new file mode 100644 index 0000000..9b3a848 --- /dev/null +++ b/Julian-600M-40B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fcd73f77744dda08a288630962396b47ed8c740bb1a9614a7d9b5ec53b76387 +size 357666336 diff --git a/Julian-600M-40B.Q5_K_M.gguf b/Julian-600M-40B.Q5_K_M.gguf new file mode 100644 index 0000000..16c5b57 --- /dev/null +++ b/Julian-600M-40B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:071b43f9486fc3925a375df975c11ac0a012b1b68a3112b80f05a02011f6d393 +size 431983136 diff --git a/Julian-600M-40B.Q5_K_S.gguf b/Julian-600M-40B.Q5_K_S.gguf new file mode 100644 index 0000000..aabc537 --- /dev/null +++ b/Julian-600M-40B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:418d5cc6a1979c7785cdca06463fb588a196fe37605f0e898c4299f56ddac508 +size 422191136 diff --git a/Julian-600M-40B.Q6_K.gguf b/Julian-600M-40B.Q6_K.gguf new file mode 100644 index 0000000..b38f9d4 --- /dev/null +++ b/Julian-600M-40B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bdd23b8465995f9678e0132448d7cc6bc84ae17d31f6dc08a333007b0c54ca0 +size 493359936 diff --git a/Julian-600M-40B.Q8_0.gguf b/Julian-600M-40B.Q8_0.gguf new file mode 100644 index 0000000..4aa2dc3 --- /dev/null +++ b/Julian-600M-40B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3431e0b9548e3bf60a40466dc93fe1d03e43fb1a0aa1997b63252d2bf4465fe1 +size 638638336 diff --git a/Julian-600M-40B.f16.gguf b/Julian-600M-40B.f16.gguf new file mode 100644 index 0000000..f46e44d --- /dev/null +++ b/Julian-600M-40B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8856b79d9c6d59b6fe7d8b3b48e7cbf9ea7ab2d1ddb23f1b43ddcbb43415f9b0 +size 1201006336 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b3890e4 --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: JulianKrgd/Julian-600M-40B +datasets: +- wikipedia +- oscar +- bigcode/the-stack-dedup +- tatsu-lab/alpaca +- databricks/databricks-dolly-15k +language: +- en +- fr +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- causal-lm +- julian +- jax +- tpu +- llama +- pretrained +--- +## About + + + + + + + + + +static quants of https://huggingface.co/JulianKrgd/Julian-600M-40B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Julian-600M-40B-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/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.Q3_K_L.gguf) | Q3_K_L | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.IQ4_XS.gguf) | IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Julian-600M-40B-GGUF/resolve/main/Julian-600M-40B.f16.gguf) | f16 | 1.3 | 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. + +