From 46331ed96fa02cc8305662b24a27ea3be3f7cacc Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 17 Jul 2026 07:18:09 +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: SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF Source: Original Platform --- .gitattributes | 52 ++++++++++++++++++ README.md | 76 ++++++++++++++++++++++++++ config.json | 3 + meta-llama-3.1-8b-instruct.Q2_K.gguf | 3 + meta-llama-3.1-8b-instruct.Q3_K_L.gguf | 3 + meta-llama-3.1-8b-instruct.Q3_K_M.gguf | 3 + meta-llama-3.1-8b-instruct.Q3_K_S.gguf | 3 + meta-llama-3.1-8b-instruct.Q4_0.gguf | 3 + meta-llama-3.1-8b-instruct.Q4_1.gguf | 3 + meta-llama-3.1-8b-instruct.Q4_K.gguf | 3 + meta-llama-3.1-8b-instruct.Q4_K_M.gguf | 3 + meta-llama-3.1-8b-instruct.Q4_K_S.gguf | 3 + meta-llama-3.1-8b-instruct.Q5_0.gguf | 3 + meta-llama-3.1-8b-instruct.Q5_1.gguf | 3 + meta-llama-3.1-8b-instruct.Q5_K.gguf | 3 + meta-llama-3.1-8b-instruct.Q5_K_M.gguf | 3 + meta-llama-3.1-8b-instruct.Q5_K_S.gguf | 3 + meta-llama-3.1-8b-instruct.Q6_K.gguf | 3 + meta-llama-3.1-8b-instruct.Q8_0.gguf | 3 + meta-llama-3.1-8b-instruct.f16.gguf | 3 + 20 files changed, 182 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 meta-llama-3.1-8b-instruct.Q2_K.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q3_K_L.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q3_K_M.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q3_K_S.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q4_0.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q4_1.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q4_K.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q4_K_M.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q4_K_S.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q5_0.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q5_1.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q5_K.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q5_K_M.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q5_K_S.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q6_K.gguf create mode 100644 meta-llama-3.1-8b-instruct.Q8_0.gguf create mode 100644 meta-llama-3.1-8b-instruct.f16.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2ef9f84 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.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-3.1-8b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd35458 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +language: +- en +- de +- fr +- it +- pt +- hi +- es +- th +pipeline_tag: text-generation +tags: +- facebook +- meta +- pytorch +- llama +- llama-3 +license: llama3.1 +license_name: llama3 +license_link: LICENSE +base_model: +- meta-llama/Meta-Llama-3.1-8B-Instruct +--- + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/64a28db2f1968b7d7f357182/vsZwOOUWI-NK6sFuJls40.png) +*This model was quantized by [SanctumAI](https://sanctum.ai). To leave feedback, join our community in [Discord](https://discord.gg/7ZNE78HJKh).* + +# Meta Llama 3 8B Instruct GGUF + +**Model creator:** [meta-llama](https://huggingface.co/meta-llama)
+**Original model**: [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
+ +## Model Summary: + +The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes (text in/text out). The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks. + +## Prompt Template: + +If you're using Sanctum app, simply use `Llama 3` model preset. + +Prompt template: + +``` +<|begin_of_text|><|start_header_id|>system<|end_header_id|> + +{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> + +{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +``` + +## Hardware Requirements Estimate + +| Name | Quant method | Size | Memory (RAM, vRAM) required | +| ---- | ---- | ---- | ---- | +| [meta-llama-3.1-8b-instruct.Q2_K.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q2_K.gguf) | Q2_K | 3.18 GB | 7.20 GB | +| [meta-llama-3.1-8b-instruct.Q3_K_S.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q3_K_S.gguf) | Q3_K_S | 3.67 GB | 7.65 GB | +| [meta-llama-3.1-8b-instruct.Q3_K_M.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q3_K_M.gguf) | Q3_K_M | 4.02 GB | 7.98 GB | +| [meta-llama-3.1-8b-instruct.Q3_K_L.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q3_K_L.gguf) | Q3_K_L | 4.32 GB | 8.27 GB | +| [meta-llama-3.1-8b-instruct.Q4_0.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q4_0.gguf) | Q4_0 | 4.66 GB | 8.58 GB | +| [meta-llama-3.1-8b-instruct.Q4_K_S.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q4_K_S.gguf) | Q4_K_S | 4.69 GB | 8.61 GB | +| [meta-llama-3.1-8b-instruct.Q4_K_M.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q4_K_M.gguf) | Q4_K_M | 4.92 GB | 8.82 GB | +| [meta-llama-3.1-8b-instruct.Q4_K.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q4_K.gguf) | Q4_K | 4.92 GB | 8.82 GB | +| [meta-llama-3.1-8b-instruct.Q4_1.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q4_1.gguf) | Q4_1 | 5.13 GB | 9.02 GB | +| [meta-llama-3.1-8b-instruct.Q5_0.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q5_0.gguf) | Q5_0 | 5.60 GB | 9.46 GB | +| [meta-llama-3.1-8b-instruct.Q5_K_S.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q5_K_S.gguf) | Q5_K_S | 5.60 GB | 9.46 GB | +| [meta-llama-3.1-8b-instruct.Q5_K_M.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q5_K_M.gguf) | Q5_K_M | 5.73 GB | 9.58 GB | +| [meta-llama-3.1-8b-instruct.Q5_K.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q5_K.gguf) | Q5_K | 5.73 GB | 9.58 GB | +| [meta-llama-3.1-8b-instruct.Q5_1.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q5_1.gguf) | Q5_1 | 6.07 GB | 9.89 GB | +| [meta-llama-3.1-8b-instruct.Q6_K.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q6_K.gguf) | Q6_K | 6.60 GB | 10.38 GB | +| [meta-llama-3.1-8b-instruct.Q8_0.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.Q8_0.gguf) | Q8_0 | 8.54 GB | 12.19 GB | +| [meta-llama-3.1-8b-instruct.f16.gguf](https://huggingface.co/SanctumAI/Meta-Llama-3.1-8B-Instruct-GGUF/blob/main/meta-llama-3.1-8b-instruct.f16.gguf) | f16 | 16.07 GB | 19.21 GB | + +## Disclaimer + +Sanctum is not the creator, originator, or owner of any Model featured in the Models section of the Sanctum application. Each Model is created and provided by third parties. Sanctum does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Model listed there. You understand that supported Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Model is the sole responsibility of the person or entity who originated such Model. Sanctum may not monitor or control the Models supported and cannot, and does not, take responsibility for any such Model. Sanctum disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Models. Sanctum further disclaims any warranty that the Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Models, your downloading of any Model, or use of any other Model provided by or through Sanctum. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a4ba21b --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "llama" +} \ No newline at end of file diff --git a/meta-llama-3.1-8b-instruct.Q2_K.gguf b/meta-llama-3.1-8b-instruct.Q2_K.gguf new file mode 100644 index 0000000..f79bca2 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45823ab346e1d98b6c7525c4a226ca5d90d68b5fff3799f7b8a00bb52c45733c +size 3179131840 diff --git a/meta-llama-3.1-8b-instruct.Q3_K_L.gguf b/meta-llama-3.1-8b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..f650c0b --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:338aa7fb2ce0b1a70ab218bfd7f7824874ef845606923f86bb3d9fde29078e35 +size 4321956800 diff --git a/meta-llama-3.1-8b-instruct.Q3_K_M.gguf b/meta-llama-3.1-8b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..96526c4 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a95a18e06348b583454753cc6ced3a656bfd341059a22eeef1ea833137eff6 +size 4018918336 diff --git a/meta-llama-3.1-8b-instruct.Q3_K_S.gguf b/meta-llama-3.1-8b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..89d159d --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c82041fda4f5b2f659cf2c0ce25dea8452b6f90ac7daedebb56c305cf70252f1 +size 3664499648 diff --git a/meta-llama-3.1-8b-instruct.Q4_0.gguf b/meta-llama-3.1-8b-instruct.Q4_0.gguf new file mode 100644 index 0000000..79ff5fe --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faf996e10380def5e4803afb580152976aa350cac383196a28cb056acd91b895 +size 4661212096 diff --git a/meta-llama-3.1-8b-instruct.Q4_1.gguf b/meta-llama-3.1-8b-instruct.Q4_1.gguf new file mode 100644 index 0000000..53dff1b --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edca0d4cec7ba6662994821286aa9d9103ce1028918a00d94e1a6e96b01e518c +size 5130253248 diff --git a/meta-llama-3.1-8b-instruct.Q4_K.gguf b/meta-llama-3.1-8b-instruct.Q4_K.gguf new file mode 100644 index 0000000..abeb114 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:549063f9cb5641ba82316da1677d8ba36b61313ffd7a56efa6fc785a6f1700be +size 4920734656 diff --git a/meta-llama-3.1-8b-instruct.Q4_K_M.gguf b/meta-llama-3.1-8b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..abeb114 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:549063f9cb5641ba82316da1677d8ba36b61313ffd7a56efa6fc785a6f1700be +size 4920734656 diff --git a/meta-llama-3.1-8b-instruct.Q4_K_S.gguf b/meta-llama-3.1-8b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..cc53a73 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b732bb40dc09c0921a5ca4ee6a15abb7f54018b13d5d8dcdf1d3d5d61ba5040 +size 4692669376 diff --git a/meta-llama-3.1-8b-instruct.Q5_0.gguf b/meta-llama-3.1-8b-instruct.Q5_0.gguf new file mode 100644 index 0000000..4047c73 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45a9cc3841c5c0040fa496d39c63e7f78b27b2c1d06f095aef9d158df303c04 +size 5599294400 diff --git a/meta-llama-3.1-8b-instruct.Q5_1.gguf b/meta-llama-3.1-8b-instruct.Q5_1.gguf new file mode 100644 index 0000000..1aaa7e8 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81ce07ad815f98dc1d2b5b935f78cb5534ae2eed364e417951b2a68c26e5c1bd +size 6068335552 diff --git a/meta-llama-3.1-8b-instruct.Q5_K.gguf b/meta-llama-3.1-8b-instruct.Q5_K.gguf new file mode 100644 index 0000000..9c83a56 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b56314e7d164901ac9ceec556dadd060d10bfb5e555c538f62eacdb47f2d2f4f +size 5732987840 diff --git a/meta-llama-3.1-8b-instruct.Q5_K_M.gguf b/meta-llama-3.1-8b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..9c83a56 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b56314e7d164901ac9ceec556dadd060d10bfb5e555c538f62eacdb47f2d2f4f +size 5732987840 diff --git a/meta-llama-3.1-8b-instruct.Q5_K_S.gguf b/meta-llama-3.1-8b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..b3ee6cf --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fa5fedd74a7da8ac3c15d16dc1989c928202313782d082cb986109f11845d11 +size 5599294400 diff --git a/meta-llama-3.1-8b-instruct.Q6_K.gguf b/meta-llama-3.1-8b-instruct.Q6_K.gguf new file mode 100644 index 0000000..3c60267 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b5e4fb221d0daa7babd02c563d68fe40fd38571696d2772533423d2ee8f923 +size 6596006848 diff --git a/meta-llama-3.1-8b-instruct.Q8_0.gguf b/meta-llama-3.1-8b-instruct.Q8_0.gguf new file mode 100644 index 0000000..eecc9a9 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea19c8cc087c29ad7cd2b4b1ed803d43d8803b3a30dcf8bef755e4c86fb954ad +size 8540771264 diff --git a/meta-llama-3.1-8b-instruct.f16.gguf b/meta-llama-3.1-8b-instruct.f16.gguf new file mode 100644 index 0000000..2bf7fbf --- /dev/null +++ b/meta-llama-3.1-8b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b74a705165a2cd109ae98260ef4218f3b159080ef59de2b6b2e18bfa03bd29e2 +size 16068891584