From 93a786c5dd4711f17ddb7fb3ccb89140d2086039 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 16 Jun 2026 22:17:12 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: QuantFactory/Llama3.1-8B-Cobalt-GGUF Source: Original Platform --- .gitattributes | 49 ++++++++++++++++ Llama3.1-8B-Cobalt.Q2_K.gguf | 3 + Llama3.1-8B-Cobalt.Q3_K_L.gguf | 3 + Llama3.1-8B-Cobalt.Q3_K_M.gguf | 3 + Llama3.1-8B-Cobalt.Q3_K_S.gguf | 3 + Llama3.1-8B-Cobalt.Q4_0.gguf | 3 + Llama3.1-8B-Cobalt.Q4_1.gguf | 3 + Llama3.1-8B-Cobalt.Q4_K_M.gguf | 3 + Llama3.1-8B-Cobalt.Q4_K_S.gguf | 3 + Llama3.1-8B-Cobalt.Q5_0.gguf | 3 + Llama3.1-8B-Cobalt.Q5_1.gguf | 3 + Llama3.1-8B-Cobalt.Q5_K_M.gguf | 3 + Llama3.1-8B-Cobalt.Q5_K_S.gguf | 3 + Llama3.1-8B-Cobalt.Q6_K.gguf | 3 + Llama3.1-8B-Cobalt.Q8_0.gguf | 3 + README.md | 103 +++++++++++++++++++++++++++++++++ configuration.json | 1 + 17 files changed, 195 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama3.1-8B-Cobalt.Q2_K.gguf create mode 100644 Llama3.1-8B-Cobalt.Q3_K_L.gguf create mode 100644 Llama3.1-8B-Cobalt.Q3_K_M.gguf create mode 100644 Llama3.1-8B-Cobalt.Q3_K_S.gguf create mode 100644 Llama3.1-8B-Cobalt.Q4_0.gguf create mode 100644 Llama3.1-8B-Cobalt.Q4_1.gguf create mode 100644 Llama3.1-8B-Cobalt.Q4_K_M.gguf create mode 100644 Llama3.1-8B-Cobalt.Q4_K_S.gguf create mode 100644 Llama3.1-8B-Cobalt.Q5_0.gguf create mode 100644 Llama3.1-8B-Cobalt.Q5_1.gguf create mode 100644 Llama3.1-8B-Cobalt.Q5_K_M.gguf create mode 100644 Llama3.1-8B-Cobalt.Q5_K_S.gguf create mode 100644 Llama3.1-8B-Cobalt.Q6_K.gguf create mode 100644 Llama3.1-8B-Cobalt.Q8_0.gguf create mode 100644 README.md create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2a6343b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q4_0.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.Q6_K.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.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Cobalt.Q5_1.gguf 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.Q3_K_L.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.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-8B-Cobalt.Q2_K.gguf b/Llama3.1-8B-Cobalt.Q2_K.gguf new file mode 100644 index 0000000..aeb9227 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e7585683fa1d6b3382c0bd32a2c9abbd50ca35883ffbf267ebc0676286c2d17 +size 3179136736 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..db0f938 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6049e3da9debaf4cc44d879535df60a00d80f34524797e410c5c2115ecaaa167 +size 4321961696 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..c6549ea --- /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:d8ced7dc5d03ec89b5d68287b59a48fd9686070c93ff1fee6208bc480bc32c4c +size 4018923232 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..83e92de --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:417f7d5107a8a24f04777ffee2ce5c52d7b6c9569931d3c41353ea140d85ace8 +size 3664504544 diff --git a/Llama3.1-8B-Cobalt.Q4_0.gguf b/Llama3.1-8B-Cobalt.Q4_0.gguf new file mode 100644 index 0000000..f2b394e --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69b542f1511eb23e341bd3d9e2be23d478a4af9c0dfe0e387c9d9b171c54ca55 +size 4661216992 diff --git a/Llama3.1-8B-Cobalt.Q4_1.gguf b/Llama3.1-8B-Cobalt.Q4_1.gguf new file mode 100644 index 0000000..4429e52 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e9ffe2da10fa61975d27061745e12a0628360dbf7ccb7ea19e76426e1e0043 +size 5130258144 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..b1dbd91 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd3b6001d1e5bc0f4c65d20841bf496f510ee0fecd9ba7ba51091e847dbbf8a +size 4920739552 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..65fa09b --- /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:e2e272a035e14297bdf324f728b488465df0775586b19a7ded5141a903defe1c +size 4692674272 diff --git a/Llama3.1-8B-Cobalt.Q5_0.gguf b/Llama3.1-8B-Cobalt.Q5_0.gguf new file mode 100644 index 0000000..f41d2fd --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46be3f4f98961ddf45ef71ba999c7aa14290d3e416c6e3a2de790c18284ff148 +size 5599299296 diff --git a/Llama3.1-8B-Cobalt.Q5_1.gguf b/Llama3.1-8B-Cobalt.Q5_1.gguf new file mode 100644 index 0000000..0c2ed7f --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b576497443cfaec805f59f50cde0ec97570b37998631afd12644e38a1cf9bbd0 +size 6068340448 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..130900d --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04412e42ca2e507b1e4882b05e69030b3f952a1d8619201d17bf7ba803a7dd66 +size 5732992736 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..31fe03e --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00c0a4cfd1c4ed128e091e9577191807ca596ed4e771518f8a61c406ff7f2b55 +size 5599299296 diff --git a/Llama3.1-8B-Cobalt.Q6_K.gguf b/Llama3.1-8B-Cobalt.Q6_K.gguf new file mode 100644 index 0000000..1784a5f --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e49eec46ec90c928ba1871a78960e05f326311cbb3cadd8ea7a9a977be41d2 +size 6596011744 diff --git a/Llama3.1-8B-Cobalt.Q8_0.gguf b/Llama3.1-8B-Cobalt.Q8_0.gguf new file mode 100644 index 0000000..756a826 --- /dev/null +++ b/Llama3.1-8B-Cobalt.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426b546e7b6e9ec22ee2c86264cec4d9529b268d2f4f7d760263ac4fae3ab593 +size 8540776160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ccfbcca --- /dev/null +++ b/README.md @@ -0,0 +1,103 @@ + +--- + +language: +- en +pipeline_tag: text-generation +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 +model_type: llama +base_model: meta-llama/Meta-Llama-3.1-8B-Instruct +datasets: +- sequelbox/Polytope +- LDJnr/Pure-Dove +license: llama3.1 + +--- + +![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ) + +# QuantFactory/Llama3.1-8B-Cobalt-GGUF +This is quantized version of [ValiantLabs/Llama3.1-8B-Cobalt](https://huggingface.co/ValiantLabs/Llama3.1-8B-Cobalt) created using llama.cpp + +# Original Model Card + + + +Cobalt is a math-instruct model built on Llama 3.1 8b. +- High quality math instruct performance within the Llama 3 Instruct chat format +- Finetuned on synthetic math-instruct data generated with Llama 3.1 405b. [Find the current version of the dataset here!](https://huggingface.co/datasets/sequelbox/Polytope) + + +## Version + +This is the **2024-08-16** release of Cobalt for Llama 3.1 8b. + +Help us and recommend Cobalt to your friends! We're excited for more Cobalt releases in the future. + +Right now, we're working on more new Build Tools to come very soon, built on Llama 3.1 :) + + +## Prompting Guide +Cobalt uses the [Llama 3.1 Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) prompt format. The example script below can be used as a starting point for general chat: + + +import transformers +import torch + +model_id = "ValiantLabs/Llama3.1-8B-Cobalt" + +pipeline = transformers.pipeline( + "text-generation", + model=model_id, + model_kwargs={"torch_dtype": torch.bfloat16}, + device_map="auto", +) + +messages = [ + {"role": "system", "content": "You are Cobalt, expert math AI."}, + {"role": "user", "content": "I'm buying a $50 shirt and a $80 pair of pants, both currently at a 25% discount. How much will I pay?"} +] + +outputs = pipeline( + messages, + max_new_tokens=1024, +) + +print(outputs[0]["generated_text"][-1]) + + +## The Model +Cobalt is built on top of Llama 3.1 8b Instruct, using math-instruct data to supplement math-instruct performance using Llama 3.1 Instruct prompt style. + +Our current version of the Cobalt math-instruct dataset is [sequelbox/Polytope](https://huggingface.co/datasets/sequelbox/Polytope), supplemented with a small selection of data from [LDJnr/Pure-Dove](https://huggingface.co/datasets/LDJnr/Pure-Dove) for general chat consistency. + + +![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg) + + +Cobalt is created by [Valiant Labs.](http://valiantlabs.ca/) + +[Check out our HuggingFace page for Shining Valiant 2 and our other Build Tools models for creators!](https://huggingface.co/ValiantLabs) + +[Follow us on X for updates on our models!](https://twitter.com/valiant_labs) + +We care about open source. +For everyone to use. + +We encourage others to finetune further from our models. diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..9e26dfe --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{} \ No newline at end of file