From 39d8ffb111c8e8fb7de1d40e585f2f1b08cedc71 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 7 Jul 2026 14:32:14 +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: QuantFactory/Llama3.2-3B-Enigma-GGUF Source: Original Platform --- .gitattributes | 49 +++++++ Llama3.2-3B-Enigma.Q2_K.gguf | 3 + Llama3.2-3B-Enigma.Q3_K_L.gguf | 3 + Llama3.2-3B-Enigma.Q3_K_M.gguf | 3 + Llama3.2-3B-Enigma.Q3_K_S.gguf | 3 + Llama3.2-3B-Enigma.Q4_0.gguf | 3 + Llama3.2-3B-Enigma.Q4_1.gguf | 3 + Llama3.2-3B-Enigma.Q4_K_M.gguf | 3 + Llama3.2-3B-Enigma.Q4_K_S.gguf | 3 + Llama3.2-3B-Enigma.Q5_0.gguf | 3 + Llama3.2-3B-Enigma.Q5_1.gguf | 3 + Llama3.2-3B-Enigma.Q5_K_M.gguf | 3 + Llama3.2-3B-Enigma.Q5_K_S.gguf | 3 + Llama3.2-3B-Enigma.Q6_K.gguf | 3 + Llama3.2-3B-Enigma.Q8_0.gguf | 3 + README.md | 230 +++++++++++++++++++++++++++++++++ configuration.json | 1 + 17 files changed, 322 insertions(+) create mode 100644 .gitattributes create mode 100644 Llama3.2-3B-Enigma.Q2_K.gguf create mode 100644 Llama3.2-3B-Enigma.Q3_K_L.gguf create mode 100644 Llama3.2-3B-Enigma.Q3_K_M.gguf create mode 100644 Llama3.2-3B-Enigma.Q3_K_S.gguf create mode 100644 Llama3.2-3B-Enigma.Q4_0.gguf create mode 100644 Llama3.2-3B-Enigma.Q4_1.gguf create mode 100644 Llama3.2-3B-Enigma.Q4_K_M.gguf create mode 100644 Llama3.2-3B-Enigma.Q4_K_S.gguf create mode 100644 Llama3.2-3B-Enigma.Q5_0.gguf create mode 100644 Llama3.2-3B-Enigma.Q5_1.gguf create mode 100644 Llama3.2-3B-Enigma.Q5_K_M.gguf create mode 100644 Llama3.2-3B-Enigma.Q5_K_S.gguf create mode 100644 Llama3.2-3B-Enigma.Q6_K.gguf create mode 100644 Llama3.2-3B-Enigma.Q8_0.gguf create mode 100644 README.md create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ef7ebb1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +Llama3.2-3B-Enigma.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-3B-Enigma.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-3B-Enigma.Q2_K.gguf b/Llama3.2-3B-Enigma.Q2_K.gguf new file mode 100644 index 0000000..5e92ff5 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d574dbf35fb8ee77a9a9fa8a6cc0b7fbf2ee60012423cb1e1033711f6ed3174 +size 1363936128 diff --git a/Llama3.2-3B-Enigma.Q3_K_L.gguf b/Llama3.2-3B-Enigma.Q3_K_L.gguf new file mode 100644 index 0000000..59c7172 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cff170e58c52bb895abe28299240ccd9fe8132bbca5dacc64470a94ce0a08a2 +size 1815348096 diff --git a/Llama3.2-3B-Enigma.Q3_K_M.gguf b/Llama3.2-3B-Enigma.Q3_K_M.gguf new file mode 100644 index 0000000..edae037 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d6acf0e34355c513d2c12a8c8cb1eb1253576320b2e2cb9be1ef02d87304f00 +size 1687159680 diff --git a/Llama3.2-3B-Enigma.Q3_K_S.gguf b/Llama3.2-3B-Enigma.Q3_K_S.gguf new file mode 100644 index 0000000..f8c3818 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0db6ed77038e95fb2ce8d40acdfa9ec1249665ab7d06226122b5ad2fb2605dec +size 1542849408 diff --git a/Llama3.2-3B-Enigma.Q4_0.gguf b/Llama3.2-3B-Enigma.Q4_0.gguf new file mode 100644 index 0000000..1f2699e --- /dev/null +++ b/Llama3.2-3B-Enigma.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0080da91d595ebc8c973e0bc7ef62252b8fd68ab16a12b176d347c4236b32e4 +size 1917191040 diff --git a/Llama3.2-3B-Enigma.Q4_1.gguf b/Llama3.2-3B-Enigma.Q4_1.gguf new file mode 100644 index 0000000..73232aa --- /dev/null +++ b/Llama3.2-3B-Enigma.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8133f8bc0961b12f0e8c850c862b69117eeaf04c295126fbd831af1f35b4abe5 +size 2093351808 diff --git a/Llama3.2-3B-Enigma.Q4_K_M.gguf b/Llama3.2-3B-Enigma.Q4_K_M.gguf new file mode 100644 index 0000000..21556cc --- /dev/null +++ b/Llama3.2-3B-Enigma.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4304e6ee1e348b228470700ec1e9423f5972333d376295195ce6cd5c70cae5e4 +size 2019378048 diff --git a/Llama3.2-3B-Enigma.Q4_K_S.gguf b/Llama3.2-3B-Enigma.Q4_K_S.gguf new file mode 100644 index 0000000..fd7d5d3 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e29e02b657ba5ae36151f7a7cb0233b6c0427daa0dafd51fcbd1564b8b04778 +size 1928201088 diff --git a/Llama3.2-3B-Enigma.Q5_0.gguf b/Llama3.2-3B-Enigma.Q5_0.gguf new file mode 100644 index 0000000..2ac1d82 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ea4cc23ad841fac3b6a318ee423f213153517548d9844091495f84ccb7a5ce +size 2269512576 diff --git a/Llama3.2-3B-Enigma.Q5_1.gguf b/Llama3.2-3B-Enigma.Q5_1.gguf new file mode 100644 index 0000000..42f05d5 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8638de96a8f35c9f009d5831a33a3ba5d4895d8489a47c6e97c7242881c4ddd +size 2445673344 diff --git a/Llama3.2-3B-Enigma.Q5_K_M.gguf b/Llama3.2-3B-Enigma.Q5_K_M.gguf new file mode 100644 index 0000000..aceafb6 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff7b57630e6013565023edaa863695d98f01528759c92f6ab14afc1a7557e2cf +size 2322154368 diff --git a/Llama3.2-3B-Enigma.Q5_K_S.gguf b/Llama3.2-3B-Enigma.Q5_K_S.gguf new file mode 100644 index 0000000..8b510b8 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:900504ea53db3aa82d8198c05f903a44ccdd5e155a3e17323835b50e3d0b0c7f +size 2269512576 diff --git a/Llama3.2-3B-Enigma.Q6_K.gguf b/Llama3.2-3B-Enigma.Q6_K.gguf new file mode 100644 index 0000000..f73706d --- /dev/null +++ b/Llama3.2-3B-Enigma.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7928638a79cd21cacd798cf12a6ddcc7cd6a3629e71edf9df028c893fe1b661 +size 2643854208 diff --git a/Llama3.2-3B-Enigma.Q8_0.gguf b/Llama3.2-3B-Enigma.Q8_0.gguf new file mode 100644 index 0000000..28f9c51 --- /dev/null +++ b/Llama3.2-3B-Enigma.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58b8b43374366405bcf2f55fc9a96a65bebeccc8f597bf612bae00e316e29bb6 +size 3421899648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a305d34 --- /dev/null +++ b/README.md @@ -0,0 +1,230 @@ + +--- + +language: +- en +license: llama3.2 +tags: +- enigma +- valiant +- valiant-labs +- llama +- llama-3.2 +- llama-3.2-instruct +- llama-3.2-instruct-3b +- llama-3 +- llama-3-instruct +- llama-3-instruct-3b +- 3b +- code +- code-instruct +- python +- conversational +- chat +- instruct +base_model: meta-llama/Llama-3.2-3B-Instruct +datasets: +- sequelbox/Tachibana +- sequelbox/Supernova +pipeline_tag: text-generation +model_type: llama +model-index: +- name: Llama3.2-3B-Enigma + results: + - task: + type: text-generation + name: Text Generation + dataset: + name: Winogrande (5-Shot) + type: winogrande + args: + num_few_shot: 5 + metrics: + - type: acc + value: 67.96 + name: acc + - task: + type: text-generation + name: Text Generation + dataset: + name: ARC Challenge (25-Shot) + type: arc-challenge + args: + num_few_shot: 25 + metrics: + - type: acc_norm + value: 47.18 + name: normalized accuracy + - task: + type: text-generation + name: Text Generation + dataset: + name: IFEval (0-Shot) + type: HuggingFaceH4/ifeval + args: + num_few_shot: 0 + metrics: + - type: inst_level_strict_acc and prompt_level_strict_acc + value: 47.75 + name: strict accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: BBH (3-Shot) + type: BBH + args: + num_few_shot: 3 + metrics: + - type: acc_norm + value: 18.81 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MATH Lvl 5 (4-Shot) + type: hendrycks/competition_math + args: + num_few_shot: 4 + metrics: + - type: exact_match + value: 6.65 + name: exact match + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: GPQA (0-shot) + type: Idavidrein/gpqa + args: + num_few_shot: 0 + metrics: + - type: acc_norm + value: 1.45 + name: acc_norm + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MuSR (0-shot) + type: TAUR-Lab/MuSR + args: + num_few_shot: 0 + metrics: + - type: acc_norm + value: 4.54 + name: acc_norm + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MMLU-PRO (5-shot) + type: TIGER-Lab/MMLU-Pro + config: main + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 15.41 + name: accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ValiantLabs/Llama3.2-3B-Enigma + name: Open LLM Leaderboard + +--- + +[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory) + + +# QuantFactory/Llama3.2-3B-Enigma-GGUF +This is quantized version of [ValiantLabs/Llama3.2-3B-Enigma](https://huggingface.co/ValiantLabs/Llama3.2-3B-Enigma) created using llama.cpp + +# Original Model Card + + + +![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/it7MY5MyLCLpFQev5dUis.jpeg) + + +Enigma is a code-instruct model built on Llama 3.2 3b. +- High quality code instruct performance with the Llama 3.2 Instruct chat format +- Finetuned on synthetic code-instruct data generated with Llama 3.1 405b. [Find the current version of the dataset here!](https://huggingface.co/datasets/sequelbox/Tachibana) +- Overall chat performance supplemented with [generalist synthetic data.](https://huggingface.co/datasets/sequelbox/Supernova) + + +## Version + +This is the **2024-09-30** release of Enigma for Llama 3.2 3b, enhancing code-instruct and general chat capabilities. + +Enigma is also available for [Llama 3.1 8b!](https://huggingface.co/ValiantLabs/Llama3.1-8B-Enigma) + +Help us and recommend Enigma to your friends! We're excited for more Enigma releases in the future. + + +## Prompting Guide +Enigma uses the [Llama 3.2 Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) prompt format. The example script below can be used as a starting point for general chat: + +```python +import transformers +import torch + +model_id = "ValiantLabs/Llama3.2-3B-Enigma" + +pipeline = transformers.pipeline( + "text-generation", + model=model_id, + model_kwargs={"torch_dtype": torch.bfloat16}, + device_map="auto", +) + +messages = [ + {"role": "system", "content": "You are Enigma, a highly capable code assistant."}, + {"role": "user", "content": "Can you explain virtualization to me?"} +] + +outputs = pipeline( + messages, + max_new_tokens=1024, +) + +print(outputs[0]["generated_text"][-1]) +``` + +## The Model +Enigma is built on top of Llama 3.2 3b Instruct, using high quality code-instruct data and general chat data in Llama 3.2 Instruct prompt style to supplement overall performance. + +Our current version of Enigma is trained on code-instruct data from [sequelbox/Tachibana](https://huggingface.co/datasets/sequelbox/Tachibana) and general chat data from [sequelbox/Supernova.](https://huggingface.co/datasets/sequelbox/Supernova) + + +![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg) + + +Enigma is created by [Valiant Labs.](http://valiantlabs.ca/) + +[Check out our HuggingFace page for Shining Valiant 2 and our other Build Tools models for creators!](https://huggingface.co/ValiantLabs) + +[Follow us on X for updates on our models!](https://twitter.com/valiant_labs) + +We care about open source. +For everyone to use. + +We encourage others to finetune further from our models. + + 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