commit 646f8a2fa55289c779749674a653796b593e9882 Author: ModelHub XC Date: Tue Aug 25 12:15:26 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: brittlewis12/Meta-Llama-3.1-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..503a613 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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.imatrix filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +meta-llama-3.1-8b-instruct.IQ4_XS.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.Q2_K_S.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_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_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 +meta-llama-3.1-8b-instruct.fp16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Meta-Llama-3.1-8B-Instruct.imatrix b/Meta-Llama-3.1-8B-Instruct.imatrix new file mode 100644 index 0000000..197de8d --- /dev/null +++ b/Meta-Llama-3.1-8B-Instruct.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fec733e485da89d0e41824f198e48bcba4d9e75d6f2192ddb28ec5df342453f +size 4988151 diff --git a/README.md b/README.md new file mode 100644 index 0000000..27e91d8 --- /dev/null +++ b/README.md @@ -0,0 +1,508 @@ +--- +base_model: meta-llama/Meta-Llama-3.1-8B-Instruct +inference: false +pipeline_tag: text-generation +language: +- en +license: other +license_name: llama3.1 +license_link: https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct/blob/main/LICENSE +model_creator: meta-llama +model_name: Meta-Llama-3.1-8B-Instruct +model_type: llama +tags: +- facebook +- meta +- pytorch +- llama +- llama-3 +- llama-3.1 +quantized_by: brittlewis12 + +--- + +# Llama 3.1 8B Instruct GGUF + +** *Updated as of 2024-07-27* ** + +**Original model**: [Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) + +**Model creator**: [Meta](https://huggingface.co/meta-llama) + +> 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. + +This repo contains GGUF format model files for Meta’s Llama 3.1 8B Instruct, +**updated as of 2024-07-27** to incorporate [long context improvements](https://github.com/ggerganov/llama.cpp/pull/8676), as well as changes to the huggingface model itself. + +Learn more on Meta’s [Llama 3.1 page](https://llama.meta.com). + +### 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 3472 (revision [b5e9546](https://github.com/ggerganov/llama.cpp/commits/b5e95468b1676e1e5c9d80d1eeeb26f542a38f42)), +using [autogguf](https://github.com/brittlewis12/autogguf). + +### Prompt template + +``` +<|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|> + + +``` + +--- + +## 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)! +- 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 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Category + Benchmark + # Shots + Metric + Llama 3 8B Instruct + Llama 3.1 8B Instruct + Llama 3 70B Instruct + Llama 3.1 70B Instruct + Llama 3.1 405B Instruct +
General + MMLU + 5 + macro_avg/acc + 68.5 + 69.4 + 82.0 + 83.6 + 87.3 +
MMLU (CoT) + 0 + macro_avg/acc + 65.3 + 73.0 + 80.9 + 86.0 + 88.6 +
MMLU-Pro (CoT) + 5 + micro_avg/acc_char + 45.5 + 48.3 + 63.4 + 66.4 + 73.3 +
IFEval + + + 76.8 + 80.4 + 82.9 + 87.5 + 88.6 +
Reasoning + ARC-C + 0 + acc + 82.4 + 83.4 + 94.4 + 94.8 + 96.9 +
GPQA + 0 + em + 34.6 + 30.4 + 39.5 + 41.7 + 50.7 +
Code + HumanEval + 0 + pass@1 + 60.4 + 72.6 + 81.7 + 80.5 + 89.0 +
MBPP ++ base version + 0 + pass@1 + 70.6 + 72.8 + 82.5 + 86.0 + 88.6 +
Multipl-E HumanEval + 0 + pass@1 + - + 50.8 + - + 65.5 + 75.2 +
Multipl-E MBPP + 0 + pass@1 + - + 52.4 + - + 62.0 + 65.7 +
Math + GSM-8K (CoT) + 8 + em_maj1@1 + 80.6 + 84.5 + 93.0 + 95.1 + 96.8 +
MATH (CoT) + 0 + final_em + 29.1 + 51.9 + 51.0 + 68.0 + 73.8 +
Tool Use + API-Bank + 0 + acc + 48.3 + 82.6 + 85.1 + 90.0 + 92.0 +
BFCL + 0 + acc + 60.3 + 76.1 + 83.0 + 84.8 + 88.5 +
Gorilla Benchmark API Bench + 0 + acc + 1.7 + 8.2 + 14.7 + 29.7 + 35.3 +
Nexus (0-shot) + 0 + macro_avg/acc + 18.1 + 38.5 + 47.8 + 56.7 + 58.7 +
Multilingual + Multilingual MGSM (CoT) + 0 + em + - + 68.9 + - + 86.9 + 91.6 +
+ +#### Multilingual benchmarks + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Category + Benchmark + Language + Llama 3.1 8B + Llama 3.1 70B + Llama 3.1 405B +
General + MMLU (5-shot, macro_avg/acc) + Portuguese + 62.12 + 80.13 + 84.95 +
Spanish + 62.45 + 80.05 + 85.08 +
Italian + 61.63 + 80.4 + 85.04 +
German + 60.59 + 79.27 + 84.36 +
French + 62.34 + 79.82 + 84.66 +
Hindi + 50.88 + 74.52 + 80.31 +
Thai + 50.32 + 72.95 + 78.21 +
diff --git a/meta-llama-3.1-8b-instruct.IQ1_M.gguf b/meta-llama-3.1-8b-instruct.IQ1_M.gguf new file mode 100644 index 0000000..b95931b --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddb4ddb9ca755f86b0b9e7076436429017d6a6a11ea521e70f9850249cf3fda0 +size 2161972416 diff --git a/meta-llama-3.1-8b-instruct.IQ1_S.gguf b/meta-llama-3.1-8b-instruct.IQ1_S.gguf new file mode 100644 index 0000000..bb9865c --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1429cc7d7547f107adca1e48b42f35aab5cd0d06993c22f464a5adba0288839d +size 2019628224 diff --git a/meta-llama-3.1-8b-instruct.IQ2_M.gguf b/meta-llama-3.1-8b-instruct.IQ2_M.gguf new file mode 100644 index 0000000..0bd3160 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d01c536ea33569094a943dc45536ba0fd14cb4a85c357472867a2080a559531 +size 2948281536 diff --git a/meta-llama-3.1-8b-instruct.IQ2_S.gguf b/meta-llama-3.1-8b-instruct.IQ2_S.gguf new file mode 100644 index 0000000..e140668 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c21b6e1668f000e997ef81645b7609d57cf4d4e9af19891c82cfecce33748f3 +size 2758489280 diff --git a/meta-llama-3.1-8b-instruct.IQ2_XS.gguf b/meta-llama-3.1-8b-instruct.IQ2_XS.gguf new file mode 100644 index 0000000..b513c18 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d57ab8d0dbc48ba3f8ad06424aed5813772f3b48560d45981f52166b262f1630 +size 2605782208 diff --git a/meta-llama-3.1-8b-instruct.IQ2_XXS.gguf b/meta-llama-3.1-8b-instruct.IQ2_XXS.gguf new file mode 100644 index 0000000..4ce4b3a --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:929c4848203162f98aad970d5c32b0d50eb6a216c1ee9f2725890c4a1ff0db14 +size 2399212736 diff --git a/meta-llama-3.1-8b-instruct.IQ3_M.gguf b/meta-llama-3.1-8b-instruct.IQ3_M.gguf new file mode 100644 index 0000000..e71be83 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07a28e4818d89b1ebb79d0ccf1c2bf7ebea528406ed4553388ffcbdf8bf05d98 +size 3784824000 diff --git a/meta-llama-3.1-8b-instruct.IQ3_S.gguf b/meta-llama-3.1-8b-instruct.IQ3_S.gguf new file mode 100644 index 0000000..7b07518 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec2da35288bb17fbfb40f67290bcb3685f3460271d5f11fd322b0cd04fc6ca37 +size 3682325696 diff --git a/meta-llama-3.1-8b-instruct.IQ3_XS.gguf b/meta-llama-3.1-8b-instruct.IQ3_XS.gguf new file mode 100644 index 0000000..0cedc8a --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86461ed871343578eeb4f5e261e573deac8fa02330a832091ddc1ffdf5229a74 +size 3518747840 diff --git a/meta-llama-3.1-8b-instruct.IQ3_XXS.gguf b/meta-llama-3.1-8b-instruct.IQ3_XXS.gguf new file mode 100644 index 0000000..2252f73 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3593312865deddc6255047a97751641f8d347b9a5f0044ba2418c379f471dc5 +size 3274912960 diff --git a/meta-llama-3.1-8b-instruct.IQ4_NL.gguf b/meta-llama-3.1-8b-instruct.IQ4_NL.gguf new file mode 100644 index 0000000..d952024 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8966dab0ef6bb637a1ac855992a892d9018d037deddf2698c122b9824a09014 +size 4677989568 diff --git a/meta-llama-3.1-8b-instruct.IQ4_XS.gguf b/meta-llama-3.1-8b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..7b5b159 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99563886353e8eecfcc1effbfb20669934948fe1ec9d0ef16e8030938210f7d4 +size 4447663296 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..e1c1807 --- /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 sha256:3dab9b5f2958df30064c1ef8d859c45c8d2466d4718b0b65b5920c874232a35c +size 3179131840 diff --git a/meta-llama-3.1-8b-instruct.Q2_K_S.gguf b/meta-llama-3.1-8b-instruct.Q2_K_S.gguf new file mode 100644 index 0000000..33539ad --- /dev/null +++ b/meta-llama-3.1-8b-instruct.Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a859d2fb26fc0c79f487129c7c7ca2140b98d4f1e3e28f2316e5952a639f54c3 +size 2988815552 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..10221bc --- /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 sha256:8b8a277383de7631e4d84e94da73940fb3519ac91cab97b86667c0f92c5ccdc6 +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..4251f0c --- /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:cc82b68601c3e0b928f36dcde0e6b9993366bcc4f14ca6eb23a69dde745d0212 +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..783ba53 --- /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:f0b56c8dc159ed4d70040a785555628b1f126026933d69f605d306ab6f602512 +size 3664499648 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..4f70538 --- /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 sha256:606ffa92823cf0563d5247613497cd670cad26019e6fc48e156bd945d7bca50c +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..d23dd19 --- /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 sha256:5ceec06d1371f163e32dea6d7a4b41a7f7f880e78f5880e863c088eee969f364 +size 4692669376 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..8fe9343 --- /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:ea18bb992104097d9d57e96e56c4b17eeb84df7099ebb975bc40cac315278f09 +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..53dd29c --- /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:d7db344eb82766ad257f92f5a9b1f259fdcc25443788213660fc641b54718581 +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..5c400d1 --- /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:a5dfbb3a8ce68994e7f5b03ea2b1da585f0766ffc699e752d1a4822fc4150a77 +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..f7d2525 --- /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 sha256:610f1831567e040a8240e21e5644eeede5aee46807cab73a59afaa8fd054a72c +size 8540771264 diff --git a/meta-llama-3.1-8b-instruct.fp16.gguf b/meta-llama-3.1-8b-instruct.fp16.gguf new file mode 100644 index 0000000..203ace6 --- /dev/null +++ b/meta-llama-3.1-8b-instruct.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32b1dce9cbb6bcc366a2fa4ce83b5e319b58f0c5cb34f65a57942ab636515f7 +size 16068891584