diff --git a/.gitattributes b/.gitattributes index 53d7257..d0a048c 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,47 +1,58 @@ *.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin 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 -*.zstandard filter=lfs diff=lfs merge=lfs -text -*.tfevents* filter=lfs diff=lfs merge=lfs -text -*.db* filter=lfs diff=lfs merge=lfs -text -*.ark* filter=lfs diff=lfs merge=lfs -text -**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text -**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text -**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text -*.safetensors filter=lfs diff=lfs merge=lfs -text -*.ckpt filter=lfs diff=lfs merge=lfs -text -*.gguf* filter=lfs diff=lfs merge=lfs -text -*.ggml filter=lfs diff=lfs merge=lfs -text -*.llamafile* filter=lfs diff=lfs merge=lfs -text -*.pt2 filter=lfs diff=lfs merge=lfs -text -*.mlmodel filter=lfs diff=lfs merge=lfs -text -*.npy filter=lfs diff=lfs merge=lfs -text -*.npz filter=lfs diff=lfs merge=lfs -text -*.pickle filter=lfs diff=lfs merge=lfs -text -*.pkl filter=lfs diff=lfs merge=lfs -text -*.tar filter=lfs diff=lfs merge=lfs -text -*.wasm filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text -*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file +*tfevents* filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v6.1-Llama3-8B.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/Einstein-v6.1-Llama3-8B-IQ1_M.gguf b/Einstein-v6.1-Llama3-8B-IQ1_M.gguf new file mode 100644 index 0000000..0af3507 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21f86f83100d4faff8d856dc5b70ac99faf57ea64189a42dd8308b67f8d8f97c +size 2161988480 diff --git a/Einstein-v6.1-Llama3-8B-IQ1_S.gguf b/Einstein-v6.1-Llama3-8B-IQ1_S.gguf new file mode 100644 index 0000000..f0140b6 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2531e4e4ebdc74a686ad87d5d15f4904ada163c15334dbfb50765f99068bac50 +size 2019644288 diff --git a/Einstein-v6.1-Llama3-8B-IQ2_M.gguf b/Einstein-v6.1-Llama3-8B-IQ2_M.gguf new file mode 100644 index 0000000..3d4f420 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23b32985e942521894f2110395f7f2ddbdcb1579d12ab37ee73805e993293e4b +size 2948299264 diff --git a/Einstein-v6.1-Llama3-8B-IQ2_S.gguf b/Einstein-v6.1-Llama3-8B-IQ2_S.gguf new file mode 100644 index 0000000..9d73d61 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f391fd4acb522dbeee5747b60ed209a6efa310fe1324f18c205488f8d745f1a3 +size 2758507008 diff --git a/Einstein-v6.1-Llama3-8B-IQ2_XS.gguf b/Einstein-v6.1-Llama3-8B-IQ2_XS.gguf new file mode 100644 index 0000000..1261046 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9393bbba20984793115ab632ece5e6f66a7b79b287abbdb8a3369a390e3c5439 +size 2605798272 diff --git a/Einstein-v6.1-Llama3-8B-IQ2_XXS.gguf b/Einstein-v6.1-Llama3-8B-IQ2_XXS.gguf new file mode 100644 index 0000000..6661835 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f0d41fe152c6ccf26d1a9d33b08af3fcc8e5e48f77da2b225f8fa10eb9838a5 +size 2399228800 diff --git a/Einstein-v6.1-Llama3-8B-IQ3_M.gguf b/Einstein-v6.1-Llama3-8B-IQ3_M.gguf new file mode 100644 index 0000000..db1b99f --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8d0d1b8c316add6a983df354c811155a87731b9f727d41f3122cc953f50aeea +size 3784843904 diff --git a/Einstein-v6.1-Llama3-8B-IQ3_S.gguf b/Einstein-v6.1-Llama3-8B-IQ3_S.gguf new file mode 100644 index 0000000..29aea55 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82fd93002aa3e62fbc407476cf942c12945f34ead033ba44c71e9ac1e91afeb7 +size 3682345600 diff --git a/Einstein-v6.1-Llama3-8B-IQ3_XS.gguf b/Einstein-v6.1-Llama3-8B-IQ3_XS.gguf new file mode 100644 index 0000000..7ef8e84 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d285f7591dbbf02a35196bbd551dfcbc64ca4bb96d05e1a844981ad965a076f0 +size 3518767744 diff --git a/Einstein-v6.1-Llama3-8B-IQ3_XXS.gguf b/Einstein-v6.1-Llama3-8B-IQ3_XXS.gguf new file mode 100644 index 0000000..85b9223 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aa53ced184d36bd7f438d4fb80ebe24e7b27a09b81676316063b49098429f3b +size 3274930688 diff --git a/Einstein-v6.1-Llama3-8B-IQ4_NL.gguf b/Einstein-v6.1-Llama3-8B-IQ4_NL.gguf new file mode 100644 index 0000000..878b167 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff8d91e769c701ae25f66565810d81b868a6f7249223852d79da65032b124cdb +size 4678011648 diff --git a/Einstein-v6.1-Llama3-8B-IQ4_XS.gguf b/Einstein-v6.1-Llama3-8B-IQ4_XS.gguf new file mode 100644 index 0000000..5e0c52b --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a7043679df0c45add3b05e404fa8c9fd36db538deae39f569004ab995f4fcf2 +size 4447684864 diff --git a/Einstein-v6.1-Llama3-8B-Q2_K.gguf b/Einstein-v6.1-Llama3-8B-Q2_K.gguf new file mode 100644 index 0000000..78e21e9 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2298db15ff26cadffe2eb15307e2eb6d278b2a56751ddd6db7f061f2996353f5 +size 3179150336 diff --git a/Einstein-v6.1-Llama3-8B-Q3_K_L.gguf b/Einstein-v6.1-Llama3-8B-Q3_K_L.gguf new file mode 100644 index 0000000..c21b70a --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a757b5ed01f279db926ee34e61ab631ead1c5694a36d3da01ae08197af0ee1c +size 4321976960 diff --git a/Einstein-v6.1-Llama3-8B-Q3_K_M.gguf b/Einstein-v6.1-Llama3-8B-Q3_K_M.gguf new file mode 100644 index 0000000..941b645 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c010cab23b319e1a20291109a5a99102a27e3b0a4dbd6653caedbe7ea189a320 +size 4018938496 diff --git a/Einstein-v6.1-Llama3-8B-Q3_K_S.gguf b/Einstein-v6.1-Llama3-8B-Q3_K_S.gguf new file mode 100644 index 0000000..b3e31c0 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9712cf94bf34af86e537ba32bf0ba392e8894cb6e01db232c182c5e139c22c91 +size 3664519808 diff --git a/Einstein-v6.1-Llama3-8B-Q4_K_M.gguf b/Einstein-v6.1-Llama3-8B-Q4_K_M.gguf new file mode 100644 index 0000000..d7abd09 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:447587bd8f60d9050232148d34fdb2d88b15b2413fd7f8e095a4606ec60b45bf +size 4920756992 diff --git a/Einstein-v6.1-Llama3-8B-Q4_K_S.gguf b/Einstein-v6.1-Llama3-8B-Q4_K_S.gguf new file mode 100644 index 0000000..eb53b7d --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827bbbcaa31ac9cca7b49b60fa4092884e4dea878433153fe4f3b2efb59c0c7a +size 4692691712 diff --git a/Einstein-v6.1-Llama3-8B-Q5_K_M.gguf b/Einstein-v6.1-Llama3-8B-Q5_K_M.gguf new file mode 100644 index 0000000..adaab17 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d34b6328341946a78e691f0de36b1a595efba37156410a6bd2d7ce4481b6530 +size 5733012224 diff --git a/Einstein-v6.1-Llama3-8B-Q5_K_S.gguf b/Einstein-v6.1-Llama3-8B-Q5_K_S.gguf new file mode 100644 index 0000000..28dd6de --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2242ad8c5152aadfdb1353b1759a0d4a6eaa207c919e781c5707c983e154bed +size 5599318784 diff --git a/Einstein-v6.1-Llama3-8B-Q6_K.gguf b/Einstein-v6.1-Llama3-8B-Q6_K.gguf new file mode 100644 index 0000000..46fab11 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:380964006b5eef42f64ff784398742d28f8c3c978f31ba757df4e9e5cee9a016 +size 6596033408 diff --git a/Einstein-v6.1-Llama3-8B-Q8_0.gguf b/Einstein-v6.1-Llama3-8B-Q8_0.gguf new file mode 100644 index 0000000..570d8ef --- /dev/null +++ b/Einstein-v6.1-Llama3-8B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b381f0d74fe7793a8551e2bf08de7b83ceb2b3935c260b45b946c9a1fb6a5cb5 +size 8540805760 diff --git a/Einstein-v6.1-Llama3-8B.imatrix b/Einstein-v6.1-Llama3-8B.imatrix new file mode 100644 index 0000000..d6e2463 --- /dev/null +++ b/Einstein-v6.1-Llama3-8B.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2661c59f42b44d840d48534e20209a871d868a2e0fd697711e8171389a40539 +size 4988166 diff --git a/README.md b/README.md index f09c7e4..4fdcdfd 100644 --- a/README.md +++ b/README.md @@ -1,47 +1,259 @@ --- -license: Apache License 2.0 - -#model-type: -##如 gpt、phi、llama、chatglm、baichuan 等 -#- gpt - -#domain: -##如 nlp、cv、audio、multi-modal -#- nlp - -#language: -##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa -#- cn - -#metrics: -##如 CIDEr、Blue、ROUGE 等 -#- CIDEr - -#tags: -##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他 -#- pretrained - -#tools: -##如 vllm、fastchat、llamacpp、AdaSeq 等 -#- vllm +language: +- en +license: other +tags: +- axolotl +- generated_from_trainer +- instruct +- finetune +- chatml +- gpt4 +- synthetic data +- science +- physics +- chemistry +- biology +- math +- llama +- llama3 +base_model: meta-llama/Meta-Llama-3-8B +datasets: +- allenai/ai2_arc +- camel-ai/physics +- camel-ai/chemistry +- camel-ai/biology +- camel-ai/math +- metaeval/reclor +- openbookqa +- mandyyyyii/scibench +- derek-thomas/ScienceQA +- TIGER-Lab/ScienceEval +- jondurbin/airoboros-3.2 +- LDJnr/Capybara +- Cot-Alpaca-GPT4-From-OpenHermes-2.5 +- STEM-AI-mtl/Electrical-engineering +- knowrohit07/saraswati-stem +- sablo/oasst2_curated +- lmsys/lmsys-chat-1m +- TIGER-Lab/MathInstruct +- bigbio/med_qa +- meta-math/MetaMathQA-40K +- openbookqa +- piqa +- metaeval/reclor +- derek-thomas/ScienceQA +- scibench +- sciq +- Open-Orca/SlimOrca +- migtissera/Synthia-v1.3 +- TIGER-Lab/ScienceEval +- allenai/WildChat +- microsoft/orca-math-word-problems-200k +- openchat/openchat_sharegpt4_dataset +- teknium/GPTeacher-General-Instruct +- m-a-p/CodeFeedback-Filtered-Instruction +- totally-not-an-llm/EverythingLM-data-V3 +- HuggingFaceH4/no_robots +- OpenAssistant/oasst_top1_2023-08-25 +- WizardLM/WizardLM_evol_instruct_70k +model-index: +- name: Einstein-v6.1-Llama3-8B + results: + - task: + type: text-generation + name: Text Generation + dataset: + name: AI2 Reasoning Challenge (25-Shot) + type: ai2_arc + config: ARC-Challenge + split: test + args: + num_few_shot: 25 + metrics: + - type: acc_norm + value: 62.46 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: HellaSwag (10-Shot) + type: hellaswag + split: validation + args: + num_few_shot: 10 + metrics: + - type: acc_norm + value: 82.41 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MMLU (5-Shot) + type: cais/mmlu + config: all + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 66.19 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: TruthfulQA (0-shot) + type: truthful_qa + config: multiple_choice + split: validation + args: + num_few_shot: 0 + metrics: + - type: mc2 + value: 55.1 + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: Winogrande (5-shot) + type: winogrande + config: winogrande_xl + split: validation + args: + num_few_shot: 5 + metrics: + - type: acc + value: 79.32 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: GSM8k (5-shot) + type: gsm8k + config: main + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 66.11 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B + name: Open LLM Leaderboard +quantized_by: bartowski +pipeline_tag: text-generation --- -### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 -#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 -SDK下载 -```bash -#安装ModelScope -pip install modelscope +## Llamacpp imatrix Quantizations of Einstein-v6.1-Llama3-8B + +Using llama.cpp release b2777 for quantization. + +Original model: https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B + +All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) + +## Prompt format + ``` -```python -#SDK模型下载 -from modelscope import snapshot_download -model_dir = snapshot_download('bartowski/Einstein-v6.1-Llama3-8B-GGUF') -``` -Git下载 -``` -#Git模型下载 -git clone https://www.modelscope.cn/bartowski/Einstein-v6.1-Llama3-8B-GGUF.git +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant + ``` -

如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。

\ No newline at end of file +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Description | +| -------- | ---------- | --------- | ----------- | +| [Einstein-v6.1-Llama3-8B-Q8_0.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-Q8_0.gguf) | Q8_0 | 8.54GB | Extremely high quality, generally unneeded but max available quant. | +| [Einstein-v6.1-Llama3-8B-Q6_K.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-Q6_K.gguf) | Q6_K | 6.59GB | Very high quality, near perfect, *recommended*. | +| [Einstein-v6.1-Llama3-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-Q5_K_M.gguf) | Q5_K_M | 5.73GB | High quality, *recommended*. | +| [Einstein-v6.1-Llama3-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-Q5_K_S.gguf) | Q5_K_S | 5.59GB | High quality, *recommended*. | +| [Einstein-v6.1-Llama3-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-Q4_K_M.gguf) | Q4_K_M | 4.92GB | Good quality, uses about 4.83 bits per weight, *recommended*. | +| [Einstein-v6.1-Llama3-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-Q4_K_S.gguf) | Q4_K_S | 4.69GB | Slightly lower quality with more space savings, *recommended*. | +| [Einstein-v6.1-Llama3-8B-IQ4_NL.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ4_NL.gguf) | IQ4_NL | 4.67GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. | +| [Einstein-v6.1-Llama3-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ4_XS.gguf) | IQ4_XS | 4.44GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Einstein-v6.1-Llama3-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-Q3_K_L.gguf) | Q3_K_L | 4.32GB | Lower quality but usable, good for low RAM availability. | +| [Einstein-v6.1-Llama3-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-Q3_K_M.gguf) | Q3_K_M | 4.01GB | Even lower quality. | +| [Einstein-v6.1-Llama3-8B-IQ3_M.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ3_M.gguf) | IQ3_M | 3.78GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Einstein-v6.1-Llama3-8B-IQ3_S.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ3_S.gguf) | IQ3_S | 3.68GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. | +| [Einstein-v6.1-Llama3-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-Q3_K_S.gguf) | Q3_K_S | 3.66GB | Low quality, not recommended. | +| [Einstein-v6.1-Llama3-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ3_XS.gguf) | IQ3_XS | 3.51GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Einstein-v6.1-Llama3-8B-IQ3_XXS.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ3_XXS.gguf) | IQ3_XXS | 3.27GB | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Einstein-v6.1-Llama3-8B-Q2_K.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-Q2_K.gguf) | Q2_K | 3.17GB | Very low quality but surprisingly usable. | +| [Einstein-v6.1-Llama3-8B-IQ2_M.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ2_M.gguf) | IQ2_M | 2.94GB | Very low quality, uses SOTA techniques to also be surprisingly usable. | +| [Einstein-v6.1-Llama3-8B-IQ2_S.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ2_S.gguf) | IQ2_S | 2.75GB | Very low quality, uses SOTA techniques to be usable. | +| [Einstein-v6.1-Llama3-8B-IQ2_XS.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ2_XS.gguf) | IQ2_XS | 2.60GB | Very low quality, uses SOTA techniques to be usable. | +| [Einstein-v6.1-Llama3-8B-IQ2_XXS.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ2_XXS.gguf) | IQ2_XXS | 2.39GB | Lower quality, uses SOTA techniques to be usable. | +| [Einstein-v6.1-Llama3-8B-IQ1_M.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ1_M.gguf) | IQ1_M | 2.16GB | Extremely low quality, *not* recommended. | +| [Einstein-v6.1-Llama3-8B-IQ1_S.gguf](https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF/blob/main/Einstein-v6.1-Llama3-8B-IQ1_S.gguf) | IQ1_S | 2.01GB | Extremely low quality, *not* recommended. | + +## Downloading using huggingface-cli + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/Einstein-v6.1-Llama3-8B-GGUF --include "Einstein-v6.1-Llama3-8B-Q4_K_M.gguf" --local-dir ./ --local-dir-use-symlinks False +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/Einstein-v6.1-Llama3-8B-GGUF --include "Einstein-v6.1-Llama3-8B-Q8_0.gguf/*" --local-dir Einstein-v6.1-Llama3-8B-Q8_0 --local-dir-use-symlinks False +``` + +You can either specify a new local-dir (Einstein-v6.1-Llama3-8B-Q8_0) or download them all in place (./) + +## Which file should I choose? + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file