From e176dc858d5ac7b58bb01091ba4c1b582d27633b Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 16 Aug 2026 03:17:13 +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: bartowski/Hercules-3.1-Mistral-7B-GGUF Source: Original Platform --- .gitattributes | 48 ++++++++++ Hercules-3.1-Mistral-7B-Q2_K.gguf | 3 + Hercules-3.1-Mistral-7B-Q3_K_L.gguf | 3 + Hercules-3.1-Mistral-7B-Q3_K_M.gguf | 3 + Hercules-3.1-Mistral-7B-Q3_K_S.gguf | 3 + Hercules-3.1-Mistral-7B-Q4_0.gguf | 3 + Hercules-3.1-Mistral-7B-Q4_K_M.gguf | 3 + Hercules-3.1-Mistral-7B-Q4_K_S.gguf | 3 + Hercules-3.1-Mistral-7B-Q5_0.gguf | 3 + Hercules-3.1-Mistral-7B-Q5_K_M.gguf | 3 + Hercules-3.1-Mistral-7B-Q5_K_S.gguf | 3 + Hercules-3.1-Mistral-7B-Q6_K.gguf | 3 + Hercules-3.1-Mistral-7B-Q8_0.gguf | 3 + Hercules-3.1-Mistral-7B-fp16.gguf | 3 + README.md | 142 ++++++++++++++++++++++++++++ configuration.json | 1 + 16 files changed, 230 insertions(+) create mode 100644 .gitattributes create mode 100644 Hercules-3.1-Mistral-7B-Q2_K.gguf create mode 100644 Hercules-3.1-Mistral-7B-Q3_K_L.gguf create mode 100644 Hercules-3.1-Mistral-7B-Q3_K_M.gguf create mode 100644 Hercules-3.1-Mistral-7B-Q3_K_S.gguf create mode 100644 Hercules-3.1-Mistral-7B-Q4_0.gguf create mode 100644 Hercules-3.1-Mistral-7B-Q4_K_M.gguf create mode 100644 Hercules-3.1-Mistral-7B-Q4_K_S.gguf create mode 100644 Hercules-3.1-Mistral-7B-Q5_0.gguf create mode 100644 Hercules-3.1-Mistral-7B-Q5_K_M.gguf create mode 100644 Hercules-3.1-Mistral-7B-Q5_K_S.gguf create mode 100644 Hercules-3.1-Mistral-7B-Q6_K.gguf create mode 100644 Hercules-3.1-Mistral-7B-Q8_0.gguf create mode 100644 Hercules-3.1-Mistral-7B-fp16.gguf create mode 100644 README.md create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6f7b95d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Hercules-3.1-Mistral-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-3.1-Mistral-7B-fp16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hercules-3.1-Mistral-7B-Q2_K.gguf b/Hercules-3.1-Mistral-7B-Q2_K.gguf new file mode 100644 index 0000000..a08e6c9 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8597174984cb9e2f7f914c9ee767cbc6c248703222ba8fa4bb1a9b23a8ccac4a +size 2719241984 diff --git a/Hercules-3.1-Mistral-7B-Q3_K_L.gguf b/Hercules-3.1-Mistral-7B-Q3_K_L.gguf new file mode 100644 index 0000000..163b440 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:512f541d3886a7d3a661ef3bd044ac7b74c168c28ab22ee5a4b44d4f68f17aa4 +size 3822024448 diff --git a/Hercules-3.1-Mistral-7B-Q3_K_M.gguf b/Hercules-3.1-Mistral-7B-Q3_K_M.gguf new file mode 100644 index 0000000..6c8b932 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9df8d1cab8ec62358be6314d6ab881e10de3cc807d688d127b6e747574e831df +size 3518985984 diff --git a/Hercules-3.1-Mistral-7B-Q3_K_S.gguf b/Hercules-3.1-Mistral-7B-Q3_K_S.gguf new file mode 100644 index 0000000..1483b39 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf20da6761353fb4514f24cf051cbe5c20d3c860f7a31eaef1e0ad9835a88d8 +size 3164567296 diff --git a/Hercules-3.1-Mistral-7B-Q4_0.gguf b/Hercules-3.1-Mistral-7B-Q4_0.gguf new file mode 100644 index 0000000..096f3c0 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:745629bf898b12b963cbccfc2c7c8e4d849171782e077e88115a1d8758560c87 +size 4108916480 diff --git a/Hercules-3.1-Mistral-7B-Q4_K_M.gguf b/Hercules-3.1-Mistral-7B-Q4_K_M.gguf new file mode 100644 index 0000000..bf7bf86 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6645d32437f9765ee350e808ec0acb58499a76cb2454d7de6fbc38f34968c9 +size 4368439040 diff --git a/Hercules-3.1-Mistral-7B-Q4_K_S.gguf b/Hercules-3.1-Mistral-7B-Q4_K_S.gguf new file mode 100644 index 0000000..bfda749 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ba3ee3a3a2f06d6503f4d1d8ac0e3e5b9e936d68f7f958a9cde1d0f2c27f1e +size 4140373760 diff --git a/Hercules-3.1-Mistral-7B-Q5_0.gguf b/Hercules-3.1-Mistral-7B-Q5_0.gguf new file mode 100644 index 0000000..b4a97d2 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a4a13c86c5389881b55116a57181e815749b2408f9eafe3d15f8948f21c2fe2 +size 4997715712 diff --git a/Hercules-3.1-Mistral-7B-Q5_K_M.gguf b/Hercules-3.1-Mistral-7B-Q5_K_M.gguf new file mode 100644 index 0000000..9b02e4d --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6df84d2cf1d8c8a783163d87ab6199e0669946de40d04b195d2a5ebf1798245 +size 5131409152 diff --git a/Hercules-3.1-Mistral-7B-Q5_K_S.gguf b/Hercules-3.1-Mistral-7B-Q5_K_S.gguf new file mode 100644 index 0000000..e2c3564 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf665a4af9f745b2999318653691ab310652bdcb9162198417bcfddbfd20f0b2 +size 4997715712 diff --git a/Hercules-3.1-Mistral-7B-Q6_K.gguf b/Hercules-3.1-Mistral-7B-Q6_K.gguf new file mode 100644 index 0000000..20d4a63 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdf618abf854cb0e702f9f6c62c8033a89d0a0457033471da3b9ab4ce677216f +size 5942064896 diff --git a/Hercules-3.1-Mistral-7B-Q8_0.gguf b/Hercules-3.1-Mistral-7B-Q8_0.gguf new file mode 100644 index 0000000..c3032e6 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:829b60d1fadde45c7389b07f096cc8419a9e413595781938341fb4ce96ab4561 +size 7695857408 diff --git a/Hercules-3.1-Mistral-7B-fp16.gguf b/Hercules-3.1-Mistral-7B-fp16.gguf new file mode 100644 index 0000000..0851448 --- /dev/null +++ b/Hercules-3.1-Mistral-7B-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4529fbd18f86c37abf59e5749a7e3617f7e2809dd68f34210969bf506bc05e2d +size 14484731584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2708dd1 --- /dev/null +++ b/README.md @@ -0,0 +1,142 @@ +--- +license: apache-2.0 +library_name: transformers +tags: +- chemistry +- biology +- code +- medical +- not-for-all-audiences +datasets: +- Locutusque/Hercules-v3.0 +model-index: +- name: Hercules-3.1-Mistral-7B + 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: 61.18 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B + 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: 83.55 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B + 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: 63.65 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B + 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: 42.83 + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B + 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: 79.01 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B + 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: 42.3 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/Hercules-3.1-Mistral-7B + name: Open LLM Leaderboard +quantized_by: bartowski +pipeline_tag: text-generation +--- + +## Llamacpp Quantizations of Hercules-3.1-Mistral-7B + +Using llama.cpp commit fa97464 for quantization. + +Original model: https://huggingface.co/Locutusque/Hercules-3.1-Mistral-7B + +Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Description | +| -------- | ---------- | --------- | ----------- | +| [Hercules-3.1-Mistral-7B-Q8_0.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. | +| [Hercules-3.1-Mistral-7B-Q6_K.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. | +| [Hercules-3.1-Mistral-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. | +| [Hercules-3.1-Mistral-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. | +| [Hercules-3.1-Mistral-7B-Q5_0.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. | +| [Hercules-3.1-Mistral-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. | +| [Hercules-3.1-Mistral-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. | +| [Hercules-3.1-Mistral-7B-Q4_0.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. | +| [Hercules-3.1-Mistral-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. | +| [Hercules-3.1-Mistral-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. | +| [Hercules-3.1-Mistral-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. | +| [Hercules-3.1-Mistral-7B-Q2_K.gguf](https://huggingface.co/bartowski/Hercules-3.1-Mistral-7B-GGUF/blob/main/Hercules-3.1-Mistral-7B-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski \ No newline at end of file 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