commit 7215e152dff9282b234ffa883a4bc05ee3d4809a Author: ModelHub XC Date: Wed Jun 3 20:18:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-8B-Cobalt-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1a740d6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Llama3.1-8B-Cobalt.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-8B-Cobalt.IQ4_XS.gguf b/Llama3.1-8B-Cobalt.IQ4_XS.gguf new file mode 100644 index 0000000..4c9853f --- /dev/null +++ b/Llama3.1-8B-Cobalt.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306c3e53b070fb1ad2cf1868d489ba95c31425a395ef9555032b240b94e0bff6 +size 4484368544 diff --git a/Llama3.1-8B-Cobalt.Q2_K.gguf b/Llama3.1-8B-Cobalt.Q2_K.gguf new file mode 100644 index 0000000..d7affe8 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca6c6968663121ea714b1910519e0891021d91d714a26fff0c23002754245a2 +size 3179137184 diff --git a/Llama3.1-8B-Cobalt.Q3_K_L.gguf b/Llama3.1-8B-Cobalt.Q3_K_L.gguf new file mode 100644 index 0000000..d2e1607 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6745382cc74c58df4f4d27e4fada729c18b239182cc40bf06e68f9aa4bd96b54 +size 4321962144 diff --git a/Llama3.1-8B-Cobalt.Q3_K_M.gguf b/Llama3.1-8B-Cobalt.Q3_K_M.gguf new file mode 100644 index 0000000..9afcfe0 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b76ed8ab67c5c100add3dafba04cde685c74fc6b625ac8d7bcc1fc9a7f61164 +size 4018923680 diff --git a/Llama3.1-8B-Cobalt.Q3_K_S.gguf b/Llama3.1-8B-Cobalt.Q3_K_S.gguf new file mode 100644 index 0000000..3332609 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d5a6bfa4eaa97b96eb790b358555628b7b68b35e7ac2ce2553c2e61829e71d +size 3664504992 diff --git a/Llama3.1-8B-Cobalt.Q4_0_4_4.gguf b/Llama3.1-8B-Cobalt.Q4_0_4_4.gguf new file mode 100644 index 0000000..edd6ac6 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:251610e144b2cb15e6a2348be66ebccecec0b39321f2c5e783abef80a5ed4053 +size 4661217440 diff --git a/Llama3.1-8B-Cobalt.Q4_K_M.gguf b/Llama3.1-8B-Cobalt.Q4_K_M.gguf new file mode 100644 index 0000000..28aa7f6 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44340f1ebbc3bf4e4e23d04ac3580c26fdc0b5717f23b45ce30743aa1eeed7ed +size 4920740000 diff --git a/Llama3.1-8B-Cobalt.Q4_K_S.gguf b/Llama3.1-8B-Cobalt.Q4_K_S.gguf new file mode 100644 index 0000000..802e817 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7453d3081769e8e488f13e5f86b8cb6b10f22848952861f3bd571ec2021b06f +size 4692674720 diff --git a/Llama3.1-8B-Cobalt.Q5_K_M.gguf b/Llama3.1-8B-Cobalt.Q5_K_M.gguf new file mode 100644 index 0000000..3bb347f --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e51a59254c2502d5fe3e84e7624ecc1152a0d1b86519decc3c191203473b955c +size 5732993184 diff --git a/Llama3.1-8B-Cobalt.Q5_K_S.gguf b/Llama3.1-8B-Cobalt.Q5_K_S.gguf new file mode 100644 index 0000000..0978fc3 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a086b495f4467c0c44a65470f0b4b9ad4addf2e47e1f10fdb91dcde3801f4053 +size 5599299744 diff --git a/Llama3.1-8B-Cobalt.Q6_K.gguf b/Llama3.1-8B-Cobalt.Q6_K.gguf new file mode 100644 index 0000000..5b052d8 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea5094b2fef8d5315b29409e3f2547999e4ed2607d47b608c2313e6d8e88b007 +size 6596012192 diff --git a/Llama3.1-8B-Cobalt.Q8_0.gguf b/Llama3.1-8B-Cobalt.Q8_0.gguf new file mode 100644 index 0000000..e87a66a --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a799c194c2ba734e97ba6ef2be79200982b90d2bd302bb416ff4760eeca43f +size 8540776608 diff --git a/Llama3.1-8B-Cobalt.f16.gguf b/Llama3.1-8B-Cobalt.f16.gguf new file mode 100644 index 0000000..a793aea --- /dev/null +++ b/Llama3.1-8B-Cobalt.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826a720ed240a45ea9b54b9f5ac39ef825055c96ad39b0e64a3632f4cee1f095 +size 16068896928 diff --git a/README.md b/README.md new file mode 100644 index 0000000..039b52d --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: ValiantLabs/Llama3.1-8B-Cobalt +datasets: +- sequelbox/Polytope +- LDJnr/Pure-Dove +language: +- en +library_name: transformers +license: llama3.1 +model_type: llama +quantized_by: mradermacher +tags: +- cobalt +- valiant +- valiant-labs +- llama +- llama-3.1 +- llama-3.1-instruct +- llama-3.1-instruct-8b +- llama-3 +- llama-3-instruct +- llama-3-instruct-8b +- 8b +- math +- math-instruct +- conversational +- chat +- instruct +--- +## About + + + + + + +static quants of https://huggingface.co/ValiantLabs/Llama3.1-8B-Cobalt + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-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/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Cobalt-GGUF/resolve/main/Llama3.1-8B-Cobalt.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. + +