From 6c79d8b2295325b0bff24b01d2818e6e74a48816 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 7 Aug 2026 08:03:16 +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: brittlewis12/Llama-3.1-Tulu-3.1-8B-GGUF Source: Original Platform --- .gitattributes | 64 +++++++++++++++++++++++ README.md | 83 ++++++++++++++++++++++++++++++ llama-3.1-tulu-3.1-8b.IQ1_M.gguf | 3 ++ llama-3.1-tulu-3.1-8b.IQ1_S.gguf | 3 ++ llama-3.1-tulu-3.1-8b.IQ2_M.gguf | 3 ++ llama-3.1-tulu-3.1-8b.IQ2_S.gguf | 3 ++ llama-3.1-tulu-3.1-8b.IQ2_XS.gguf | 3 ++ llama-3.1-tulu-3.1-8b.IQ2_XXS.gguf | 3 ++ llama-3.1-tulu-3.1-8b.IQ3_M.gguf | 3 ++ llama-3.1-tulu-3.1-8b.IQ3_S.gguf | 3 ++ llama-3.1-tulu-3.1-8b.IQ3_XS.gguf | 3 ++ llama-3.1-tulu-3.1-8b.IQ3_XXS.gguf | 3 ++ llama-3.1-tulu-3.1-8b.IQ4_NL.gguf | 3 ++ llama-3.1-tulu-3.1-8b.IQ4_XS.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q2_K.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q2_K_S.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q3_K_L.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q3_K_M.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q3_K_S.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q4_0.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q4_1.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q4_K_M.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q4_K_S.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q5_0.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q5_1.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q5_K_M.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q5_K_S.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q6_K.gguf | 3 ++ llama-3.1-tulu-3.1-8b.Q8_0.gguf | 3 ++ llama-3.1-tulu-3.1-8b.f16.gguf | 3 ++ llama-3.1-tulu-3.1-8b.imatrix | 3 ++ 31 files changed, 234 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 llama-3.1-tulu-3.1-8b.IQ1_M.gguf create mode 100644 llama-3.1-tulu-3.1-8b.IQ1_S.gguf create mode 100644 llama-3.1-tulu-3.1-8b.IQ2_M.gguf create mode 100644 llama-3.1-tulu-3.1-8b.IQ2_S.gguf create mode 100644 llama-3.1-tulu-3.1-8b.IQ2_XS.gguf create mode 100644 llama-3.1-tulu-3.1-8b.IQ2_XXS.gguf create mode 100644 llama-3.1-tulu-3.1-8b.IQ3_M.gguf create mode 100644 llama-3.1-tulu-3.1-8b.IQ3_S.gguf create mode 100644 llama-3.1-tulu-3.1-8b.IQ3_XS.gguf create mode 100644 llama-3.1-tulu-3.1-8b.IQ3_XXS.gguf create mode 100644 llama-3.1-tulu-3.1-8b.IQ4_NL.gguf create mode 100644 llama-3.1-tulu-3.1-8b.IQ4_XS.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q2_K.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q2_K_S.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q3_K_L.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q3_K_M.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q3_K_S.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q4_0.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q4_1.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q4_K_M.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q4_K_S.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q5_0.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q5_1.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q5_K_M.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q5_K_S.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q6_K.gguf create mode 100644 llama-3.1-tulu-3.1-8b.Q8_0.gguf create mode 100644 llama-3.1-tulu-3.1-8b.f16.gguf create mode 100644 llama-3.1-tulu-3.1-8b.imatrix diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b2ac489 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,64 @@ +*.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 +llama-3.1-tulu-3.1-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.imatrix filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-3.1-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e833c03 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: allenai/Llama-3.1-Tulu-3.1-8B +pipeline_tag: text-generation +inference: true +language: +- en +license: llama3.1 +model_creator: allenai +model_name: Llama-3.1-Tulu-3.1-8B +model_type: llama +datasets: + - allenai/RLVR-GSM-MATH-IF-Mixed-Constraints +quantized_by: brittlewis12 + +--- + +# Tülu 3.1 8B GGUF + +**Original model**: [Tülu 3.1 8B](https://huggingface.co/allenai/Llama-3.1-Tulu-3.1-8B) + +**Model creator**: [allenai](https://huggingface.co/allenai) + +> **Version 3.1 update**: The new version of our Tülu model is from an improvement only in the final RL stage of training. We switched from PPO to GRPO (no reward model) and did further hyperparameter tuning to achieve substantial performance improvements across the board over the original Tülu 3 8B model, as shown in the comparison below: + +> Tülu 3 is a leading instruction following model family, offering a post-training package with fully open-source data, code, and recipes designed to serve as a comprehensive guide for modern techniques. This is one step of a bigger process to training fully open-source models, like our OLMo models. Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval. + + +This repo contains GGUF format model files for the Allen Institute for AI’s Tülu 3.1 8B. + +### What is GGUF? + +GGUF is a file format for representing AI models. It is the third version of the format, +introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. +Converted with llama.cpp build 4699 (revision [31afcbe](https://github.com/ggerganov/llama.cpp/commits/31afcbee0eebbc998ab311aa314e389d60aa2127)), +using [autogguf-rs](https://github.com/brittlewis12/autogguf-rs). + +### Prompt template + +``` +<|system|> +{{system_message}} +<|user|> +{{prompt}} +<|assistant|> +{{assistant_message}}<|end_of_text|> + +``` + +--- + +## Download & run with [cnvrs](https://twitter.com/cnvrsai) on iPhone, iPad, and Mac! + +![cnvrs.ai](https://pbs.twimg.com/profile_images/1744049151241797632/0mIP-P9e_400x400.jpg) + +[cnvrs](https://testflight.apple.com/join/sFWReS7K) is the best app for private, local AI on your device: +- create & save **Characters** with custom system prompts & temperature settings +- download and experiment with any **GGUF model** you can [find on HuggingFace](https://huggingface.co/models?library=gguf)! + * or, use an API key with the chat completions-compatible model provider of your choice -- ChatGPT, Claude, Gemini, DeepSeek, & more! +- make it your own with custom **Theme colors** +- powered by Metal ⚡️ & [Llama.cpp](https://github.com/ggerganov/llama.cpp), with **haptics** during response streaming! +- **try it out** yourself today, on [Testflight](https://testflight.apple.com/join/sFWReS7K)! +- follow [cnvrs on twitter](https://twitter.com/cnvrsai) to stay up to date + +--- + +## Original Model Evaluation + +| Benchmark (eval) | Tülu 3 SFT 8B | Tülu 3 DPO 8B | Tülu 3 8B | **Tülu 3.1 8B (NEW)** | Llama 3.1 8B Instruct | Qwen 2.5 7B Instruct | Magpie 8B | Gemma 2 9B Instruct | Ministral 8B Instruct | +|---------------------------------|--------------|--------------|-----------|------------|------------------------|----------------------|-----------|---------------------|-----------------------| +| **Avg.** | 60.4 | 64.4 | 64.8 | 66.3 | 62.2 | **66.5** | 44.7 | 55.2 | 58.3 | +| **MMLU (0 shot, CoT)** | 65.9 | 68.7 | 68.2 | 69.5 | 71.2 | **76.6** | 62.0 | 74.6 | 68.5 | +| **PopQA (15 shot)** | **29.3** | 29.3 | 29.1 | 30.2 | 20.2 | 18.1 | 22.5 | 28.3 | 20.2 | +| **TruthfulQA (6 shot)** | 46.8 | 56.1 | 55.0 | 59.9 | 55.1 | **63.1** | 57.0 | 61.4 | 55.5 | +| **BigBenchHard (3 shot, CoT)** | **67.9** | 65.8 | 66.0 | 68.9 | 62.8 | 70.2 | 0.9 | 2.5 | 56.2 | +| **DROP (3 shot)** | 61.3 | 62.5 | 62.6 | **63.9** | 61.5 | 54.4 | 49.4 | 58.8 | 56.2 | +| **MATH (4 shot CoT, Flex)** | 31.5 | 42.0 |43.7 | 47.8 | 42.5 | **69.9** | 5.1 | 29.8 | 40.0 | +| **GSM8K (8 shot, CoT)** | 76.2 | 84.3 | 87.6 | **90.0** | 83.4 | 83.8 | 61.2 | 79.7 | 80.0 | +| **HumanEval (pass@10)** | 86.2 | 83.9 | 83.9 | 84.8 | 86.3 | **93.1** | 75.4 | 71.7 | 91.0 | +| **HumanEval+ (pass@10)** | 81.4 | 78.6 | 79.2 | 80.4 | 82.9 | **89.7** | 69.1 | 67.0 | 88.5 | +| **IFEval (prompt loose)** | 72.8 | 81.1 | 82.4 | **83.9** | 80.6 | 74.7 | 38.8 | 69.9 | 56.4 | +| **AlpacaEval 2 (LC % win)** | 12.4 | 33.5 | 34.5 | 34.9 | 24.2 | 29.0 | **49.0** | 43.7 | 31.4 | +| **Safety (6 task avg.)** | **93.1** | 87.2 | 85.5 | 81.2 | 75.2 | 75.0 | 46.4 | 75.5 | 56.2 | + diff --git a/llama-3.1-tulu-3.1-8b.IQ1_M.gguf b/llama-3.1-tulu-3.1-8b.IQ1_M.gguf new file mode 100644 index 0000000..bf53670 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e11c24c35e898d9cadd347a06549a27c844bf2dbe0503d26da34a4353c83583 +size 2162006912 diff --git a/llama-3.1-tulu-3.1-8b.IQ1_S.gguf b/llama-3.1-tulu-3.1-8b.IQ1_S.gguf new file mode 100644 index 0000000..58157ab --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f21c4c368601410700f33e66caddf7741ba13629971ad80ea271fc952d2e1fe8 +size 2019662720 diff --git a/llama-3.1-tulu-3.1-8b.IQ2_M.gguf b/llama-3.1-tulu-3.1-8b.IQ2_M.gguf new file mode 100644 index 0000000..2ec910e --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d4c3a10e9386169cac4075a9847dc46a94d60d91d0e95a0b1552def36fcba3c +size 2948319360 diff --git a/llama-3.1-tulu-3.1-8b.IQ2_S.gguf b/llama-3.1-tulu-3.1-8b.IQ2_S.gguf new file mode 100644 index 0000000..95b5e25 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f8f98d0dbcb43e24c158248fcd00d544bdad0a47c7c7f9d9ace9d5d16f77d9 +size 2758527104 diff --git a/llama-3.1-tulu-3.1-8b.IQ2_XS.gguf b/llama-3.1-tulu-3.1-8b.IQ2_XS.gguf new file mode 100644 index 0000000..1077e93 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355c2a333039c272661db7547bf0f2ad1caefd059f3b1d2bafa4e03bff5cb10f +size 2605816704 diff --git a/llama-3.1-tulu-3.1-8b.IQ2_XXS.gguf b/llama-3.1-tulu-3.1-8b.IQ2_XXS.gguf new file mode 100644 index 0000000..9fe9d41 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a597b2ca6666478c5cab0509b247a83aadcc7fb9cd0e6db826eed77a2635a210 +size 2399247232 diff --git a/llama-3.1-tulu-3.1-8b.IQ3_M.gguf b/llama-3.1-tulu-3.1-8b.IQ3_M.gguf new file mode 100644 index 0000000..ee3e23b --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dacbede04b6e53c52d2885502f1e774b169f7588081df71359920d91433c33e0 +size 3784866176 diff --git a/llama-3.1-tulu-3.1-8b.IQ3_S.gguf b/llama-3.1-tulu-3.1-8b.IQ3_S.gguf new file mode 100644 index 0000000..c1879fe --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb9961eb2145c98b613d79e0ab97d7a9235a035fefc9f05868cc2e5a25201ddd +size 3682367872 diff --git a/llama-3.1-tulu-3.1-8b.IQ3_XS.gguf b/llama-3.1-tulu-3.1-8b.IQ3_XS.gguf new file mode 100644 index 0000000..e5a3470 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:122ac0b82e81d91ebf9d367d6d92ad6588196dc9253c008fc6b9c4fcc947bd1c +size 3518790016 diff --git a/llama-3.1-tulu-3.1-8b.IQ3_XXS.gguf b/llama-3.1-tulu-3.1-8b.IQ3_XXS.gguf new file mode 100644 index 0000000..3d7c967 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7111d8aef8d152cf843dcdad06b8919715fc595f2e51477fdb1b4aa8b70e1c42 +size 3274950784 diff --git a/llama-3.1-tulu-3.1-8b.IQ4_NL.gguf b/llama-3.1-tulu-3.1-8b.IQ4_NL.gguf new file mode 100644 index 0000000..83fdf5e --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:899b024558d9662c806a1952ac667f1e331e17afcfcbd913b94812ec6038b661 +size 4678036096 diff --git a/llama-3.1-tulu-3.1-8b.IQ4_XS.gguf b/llama-3.1-tulu-3.1-8b.IQ4_XS.gguf new file mode 100644 index 0000000..49f2526 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2f239e0980795425d85c395cb6479ae71623332ea8b5553d98cbd978b93c74 +size 4447708800 diff --git a/llama-3.1-tulu-3.1-8b.Q2_K.gguf b/llama-3.1-tulu-3.1-8b.Q2_K.gguf new file mode 100644 index 0000000..56946c0 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6230e27fb0d2057e7c50a5032ca6e61be281b9046ca24ea98618f9960fc35205 +size 3179170688 diff --git a/llama-3.1-tulu-3.1-8b.Q2_K_S.gguf b/llama-3.1-tulu-3.1-8b.Q2_K_S.gguf new file mode 100644 index 0000000..94ecc5c --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3575c693143aee3af6822c55c5bd68e0ef7bddb42c134985f9a45d608d5f998 +size 2988854400 diff --git a/llama-3.1-tulu-3.1-8b.Q3_K_L.gguf b/llama-3.1-tulu-3.1-8b.Q3_K_L.gguf new file mode 100644 index 0000000..f246b8e --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a109cad6c3898dc5f2a88aab3e597265739f6498c31105d5983b8af86706259c +size 4321998976 diff --git a/llama-3.1-tulu-3.1-8b.Q3_K_M.gguf b/llama-3.1-tulu-3.1-8b.Q3_K_M.gguf new file mode 100644 index 0000000..6159657 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:939f77cf618ce8e8fedbd731a07fd9e14a64b2cf95e236482e8a62a7335b74b4 +size 4018960512 diff --git a/llama-3.1-tulu-3.1-8b.Q3_K_S.gguf b/llama-3.1-tulu-3.1-8b.Q3_K_S.gguf new file mode 100644 index 0000000..ab75f3c --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab879de656267d653ca004335bf215051084946ef4c4b465db8a9ad5d1d63276 +size 3664541824 diff --git a/llama-3.1-tulu-3.1-8b.Q4_0.gguf b/llama-3.1-tulu-3.1-8b.Q4_0.gguf new file mode 100644 index 0000000..d0f57f4 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bbfd8b45623cce4eac6ba3e8a355a4a0e8c8614d5d9d119b941973d68bcd526 +size 4661258624 diff --git a/llama-3.1-tulu-3.1-8b.Q4_1.gguf b/llama-3.1-tulu-3.1-8b.Q4_1.gguf new file mode 100644 index 0000000..0b9aa17 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d349538411c66efd8cc7e8814b7fc7522c28ea7dff30adc32bd4da745b1dbacc +size 5130301824 diff --git a/llama-3.1-tulu-3.1-8b.Q4_K_M.gguf b/llama-3.1-tulu-3.1-8b.Q4_K_M.gguf new file mode 100644 index 0000000..0988db1 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9f5e8b8b9a8ee1a347569ee8bc7198db21ed5602225d647d3871c1a1869e463 +size 4920781184 diff --git a/llama-3.1-tulu-3.1-8b.Q4_K_S.gguf b/llama-3.1-tulu-3.1-8b.Q4_K_S.gguf new file mode 100644 index 0000000..8048212 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5551871a474f5caafad3628ad52172a9ce59b4b23542caa37e88598ab889b1 +size 4692715904 diff --git a/llama-3.1-tulu-3.1-8b.Q5_0.gguf b/llama-3.1-tulu-3.1-8b.Q5_0.gguf new file mode 100644 index 0000000..bb535a9 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77b8281dd173baf20e36caeca0a4e725a4ba84f5f94fb908ccdf65bdb586b1b +size 5599345024 diff --git a/llama-3.1-tulu-3.1-8b.Q5_1.gguf b/llama-3.1-tulu-3.1-8b.Q5_1.gguf new file mode 100644 index 0000000..2a7089b --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd6718ee0bd9c43104b1b72aa48f1e6b588fe816f2d1b8a25266a1556ee1b14d +size 6068388224 diff --git a/llama-3.1-tulu-3.1-8b.Q5_K_M.gguf b/llama-3.1-tulu-3.1-8b.Q5_K_M.gguf new file mode 100644 index 0000000..f7a7894 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8337e9c38b6a989724bfc17c1254c6a6162df019bc8d3826a39cef1145e2dc +size 5733038464 diff --git a/llama-3.1-tulu-3.1-8b.Q5_K_S.gguf b/llama-3.1-tulu-3.1-8b.Q5_K_S.gguf new file mode 100644 index 0000000..7434356 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88953d6d63ed0a8ad7eeeedd8110864639f432eead5cfafd8a3ed4af498e9971 +size 5599345024 diff --git a/llama-3.1-tulu-3.1-8b.Q6_K.gguf b/llama-3.1-tulu-3.1-8b.Q6_K.gguf new file mode 100644 index 0000000..0ff0134 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:070d062043504c8ccb053f3da0556a23140ee0b881b36e618b04b3cb8fa4495b +size 6596061824 diff --git a/llama-3.1-tulu-3.1-8b.Q8_0.gguf b/llama-3.1-tulu-3.1-8b.Q8_0.gguf new file mode 100644 index 0000000..d5a127a --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e40872eaacd6c875465ead3b3e3e4125e24bae9b11fbe7f49391632e27c067a +size 8540842112 diff --git a/llama-3.1-tulu-3.1-8b.f16.gguf b/llama-3.1-tulu-3.1-8b.f16.gguf new file mode 100644 index 0000000..09967fe --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a7a4a61bd2f6e1dea48dfa9a14c4828c4205891dabf3b95ae035a6bf5fa8f5 +size 16069023872 diff --git a/llama-3.1-tulu-3.1-8b.imatrix b/llama-3.1-tulu-3.1-8b.imatrix new file mode 100644 index 0000000..c6d9329 --- /dev/null +++ b/llama-3.1-tulu-3.1-8b.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb2264238f79c52706e108d927f0bbbb39f5b8109032ca9a56e877fbed0c9c3 +size 4988154