From b725e21742abb3c2ac6b961dd1a8c2039d6ca59d Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 8 May 2026 17:59:26 +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: Mungert/granite-3.1-1b-a400m-instruct-GGUF Source: Original Platform --- .gitattributes | 68 +++ README.md | 420 +++++++++++++++++++ granite-3.1-1b-a400m-instruct-bf16.gguf | 3 + granite-3.1-1b-a400m-instruct-bf16_q8_0.gguf | 3 + granite-3.1-1b-a400m-instruct-f16_q8_0.gguf | 3 + granite-3.1-1b-a400m-instruct-iq3_m.gguf | 3 + granite-3.1-1b-a400m-instruct-iq3_s.gguf | 3 + granite-3.1-1b-a400m-instruct-iq3_xs.gguf | 3 + granite-3.1-1b-a400m-instruct-iq3_xxs.gguf | 3 + granite-3.1-1b-a400m-instruct-iq4_nl.gguf | 3 + granite-3.1-1b-a400m-instruct-iq4_xs.gguf | 3 + granite-3.1-1b-a400m-instruct-q3_k_m.gguf | 3 + granite-3.1-1b-a400m-instruct-q3_k_s.gguf | 3 + granite-3.1-1b-a400m-instruct-q4_0.gguf | 3 + granite-3.1-1b-a400m-instruct-q4_1.gguf | 3 + granite-3.1-1b-a400m-instruct-q5_0.gguf | 3 + granite-3.1-1b-a400m-instruct-q5_1.gguf | 3 + granite-3.1-1b-a400m-instruct-q5_k_m.gguf | 3 + granite-3.1-1b-a400m-instruct-q5_k_s.gguf | 3 + granite-3.1-1b-a400m-instruct-q6_k_m.gguf | 3 + granite-3.1-1b-a400m-instruct-q8_0.gguf | 3 + granite-3.1-1b-a400m-instruct.imatrix | 3 + 22 files changed, 548 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 granite-3.1-1b-a400m-instruct-bf16.gguf create mode 100644 granite-3.1-1b-a400m-instruct-bf16_q8_0.gguf create mode 100644 granite-3.1-1b-a400m-instruct-f16_q8_0.gguf create mode 100644 granite-3.1-1b-a400m-instruct-iq3_m.gguf create mode 100644 granite-3.1-1b-a400m-instruct-iq3_s.gguf create mode 100644 granite-3.1-1b-a400m-instruct-iq3_xs.gguf create mode 100644 granite-3.1-1b-a400m-instruct-iq3_xxs.gguf create mode 100644 granite-3.1-1b-a400m-instruct-iq4_nl.gguf create mode 100644 granite-3.1-1b-a400m-instruct-iq4_xs.gguf create mode 100644 granite-3.1-1b-a400m-instruct-q3_k_m.gguf create mode 100644 granite-3.1-1b-a400m-instruct-q3_k_s.gguf create mode 100644 granite-3.1-1b-a400m-instruct-q4_0.gguf create mode 100644 granite-3.1-1b-a400m-instruct-q4_1.gguf create mode 100644 granite-3.1-1b-a400m-instruct-q5_0.gguf create mode 100644 granite-3.1-1b-a400m-instruct-q5_1.gguf create mode 100644 granite-3.1-1b-a400m-instruct-q5_k_m.gguf create mode 100644 granite-3.1-1b-a400m-instruct-q5_k_s.gguf create mode 100644 granite-3.1-1b-a400m-instruct-q6_k_m.gguf create mode 100644 granite-3.1-1b-a400m-instruct-q8_0.gguf create mode 100644 granite-3.1-1b-a400m-instruct.imatrix diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..97dbd0e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,68 @@ +*.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 +granite-3.1-1b-a400m-instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q4_1.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q5_1.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct.imatrix filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-bf16_q4_k.gguf.tmp filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-q4_k_l.gguf.tmp filter=lfs diff=lfs merge=lfs -text +granite-3.1-1b-a400m-instruct-f16_q4_k.gguf.tmp filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d7c5deb --- /dev/null +++ b/README.md @@ -0,0 +1,420 @@ +--- +pipeline_tag: text-generation +inference: false +license: apache-2.0 +library_name: transformers +tags: +- language +- granite-3.1 +base_model: +- ibm-granite/granite-3.1-1b-a400m-base +--- + +# granite-3.1-1b-a400m-instruct GGUF Models + + +## Model Generation Details + +This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`0a5a3b5c`](https://github.com/ggerganov/llama.cpp/commit/0a5a3b5cdfd887cf0f8e09d9ff89dee130cfcdde). + + + + + + +--- + + + Click here to get info on choosing the right GGUF model format + + +--- + + + + + + +# Granite-3.1-1B-A400M-Instruct + +**Model Summary:** +Granite-3.1-1B-A400M-Instruct is a 8B parameter long-context instruct model finetuned from Granite-3.1-1B-A400M-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets tailored for solving long context problems. This model is developed using a diverse set of techniques with a structured chat format, including supervised finetuning, model alignment using reinforcement learning, and model merging. + +- **Developers:** Granite Team, IBM +- **GitHub Repository:** [ibm-granite/granite-3.1-language-models](https://github.com/ibm-granite/granite-3.1-language-models) +- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/) +- **Paper:** [Granite 3.1 Language Models (coming soon)](https://huggingface.co/collections/ibm-granite/granite-31-language-models-6751dbbf2f3389bec5c6f02d) +- **Release Date**: December 18th, 2024 +- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) + +**Supported Languages:** +English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 3.1 models for languages beyond these 12 languages. + +**Intended Use:** +The model is designed to respond to general instructions and can be used to build AI assistants for multiple domains, including business applications. + +*Capabilities* +* Summarization +* Text classification +* Text extraction +* Question-answering +* Retrieval Augmented Generation (RAG) +* Code related tasks +* Function-calling tasks +* Multilingual dialog use cases +* Long-context tasks including long document/meeting summarization, long document QA, etc. + +**Generation:** +This is a simple example of how to use Granite-3.1-1B-A400M-Instruct model. + +Install the following libraries: + +```shell +pip install torch torchvision torchaudio +pip install accelerate +pip install transformers +``` +Then, copy the snippet from the section that is relevant for your use case. + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +device = "auto" +model_path = "ibm-granite/granite-3.1-1b-a400m-instruct" +tokenizer = AutoTokenizer.from_pretrained(model_path) +# drop device_map if running on CPU +model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device) +model.eval() +# change input text as desired +chat = [ + { "role": "user", "content": "Please list one IBM Research laboratory located in the United States. You should only output its name and location." }, +] +chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) +# tokenize the text +input_tokens = tokenizer(chat, return_tensors="pt").to(device) +# generate output tokens +output = model.generate(**input_tokens, + max_new_tokens=100) +# decode output tokens into text +output = tokenizer.batch_decode(output) +# print output +print(output) +``` + +**Evaluation Results:** + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
HuggingFace Open LLM Leaderboard V1
ModelsARC-ChallengeHellaswagMMLUTruthfulQAWinograndeGSM8KAvg
Granite-3.1-8B-Instruct62.6284.4865.3466.2375.3773.8471.31
Granite-3.1-2B-Instruct54.6175.1455.3159.4267.4852.7660.79
Granite-3.1-3B-A800M-Instruct50.4273.0152.1949.7164.8748.9756.53
Granite-3.1-1B-A400M-Instruct42.6665.9726.1346.7762.3533.8846.29
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
HuggingFace Open LLM Leaderboard V2
ModelsIFEvalBBHMATH Lvl 5GPQAMUSRMMLU-ProAvg
Granite-3.1-8B-Instruct72.0834.0921.688.2819.0128.1930.55
Granite-3.1-2B-Instruct62.8621.8211.335.264.8720.2121.06
Granite-3.1-3B-A800M-Instruct55.1616.6910.355.152.5112.7517.1
Granite-3.1-1B-A400M-Instruct46.866.184.0800.782.4110.05
+ +**Model Architecture:** +Granite-3.1-1B-A400M-Instruct is based on a decoder-only dense transformer architecture. Core components of this architecture are: GQA and RoPE, MLP with SwiGLU, RMSNorm, and shared input/output embeddings. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Model2B Dense8B Dense1B MoE3B MoE
Embedding size2048409610241536
Number of layers40402432
Attention head size641286464
Number of attention heads32321624
Number of KV heads8888
MLP hidden size819212800512512
MLP activationSwiGLUSwiGLUSwiGLUSwiGLU
Number of experts——3240
MoE TopK——88
Initialization std0.10.10.10.1
Sequence length128K128K128K128K
Position embeddingRoPERoPERoPERoPE
# Parameters2.5B8.1B1.3B3.3B
# Active parameters2.5B8.1B400M800M
# Training tokens12T12T10T10T
+ +**Training Data:** +Overall, our SFT data is largely comprised of three key sources: (1) publicly available datasets with permissive license, (2) internal synthetic data targeting specific capabilities including long-context tasks, and (3) very small amounts of human-curated data. A detailed attribution of datasets can be found in the [Granite 3.0 Technical Report](https://github.com/ibm-granite/granite-3.0-language-models/blob/main/paper.pdf), [Granite 3.1 Technical Report (coming soon)](https://huggingface.co/collections/ibm-granite/granite-31-language-models-6751dbbf2f3389bec5c6f02d), and [Accompanying Author List](https://github.com/ibm-granite/granite-3.0-language-models/blob/main/author-ack.pdf). + +**Infrastructure:** +We train Granite 3.1 Language Models using IBM's super computing cluster, Blue Vela, which is outfitted with NVIDIA H100 GPUs. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs. + +**Ethical Considerations and Limitations:** +Granite 3.1 Instruct Models are primarily finetuned using instruction-response pairs mostly in English, but also multilingual data covering eleven languages. Although this model can handle multilingual dialog use cases, its performance might not be similar to English tasks. In such case, introducing a small number of examples (few-shot) can help the model in generating more accurate outputs. While this model has been aligned by keeping safety in consideration, the model may in some cases produce inaccurate, biased, or unsafe responses to user prompts. So we urge the community to use this model with proper safety testing and tuning tailored for their specific tasks. + +**Resources** +- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite +- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/ +- 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources + + + + + +--- + +# 🚀 If you find these models useful + +Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**: + +👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) + + +The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder) + +💬 **How to test**: + Choose an **AI assistant type**: + - `TurboLLM` (GPT-4.1-mini) + - `HugLLM` (Hugginface Open-source models) + - `TestLLM` (Experimental CPU-only) + +### **What I’m Testing** +I’m pushing the limits of **small open-source models for AI network monitoring**, specifically: +- **Function calling** against live network services +- **How small can a model go** while still handling: + - Automated **Nmap security scans** + - **Quantum-readiness checks** + - **Network Monitoring tasks** + +🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space): +- ✅ **Zero-configuration setup** +- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low. +- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate! + +### **Other Assistants** +🟢 **TurboLLM** – Uses **gpt-4.1-mini** : +- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. +- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents** +- **Real-time network diagnostics and monitoring** +- **Security Audits** +- **Penetration testing** (Nmap/Metasploit) + +🔵 **HugLLM** – Latest Open-source models: +- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita. + +### 💡 **Example commands you could test**: +1. `"Give me info on my websites SSL certificate"` +2. `"Check if my server is using quantum safe encyption for communication"` +3. `"Run a comprehensive security audit on my server"` +4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution! + +### Final Word + +I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful. + +If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone. + +I'm also open to job opportunities or sponsorship. + +Thank you! 😊 diff --git a/granite-3.1-1b-a400m-instruct-bf16.gguf b/granite-3.1-1b-a400m-instruct-bf16.gguf new file mode 100644 index 0000000..9b374f5 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ef894f4e5acfdeb5465a38d18158a85d9a2bee1595b5100174c41e6b6b6139 +size 2672669632 diff --git a/granite-3.1-1b-a400m-instruct-bf16_q8_0.gguf b/granite-3.1-1b-a400m-instruct-bf16_q8_0.gguf new file mode 100644 index 0000000..249e489 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-bf16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d12816f71a96f623a3dadef57dc3bc8dd32f36aed5efb34802c75bc6e6f9b8e7 +size 1504818112 diff --git a/granite-3.1-1b-a400m-instruct-f16_q8_0.gguf b/granite-3.1-1b-a400m-instruct-f16_q8_0.gguf new file mode 100644 index 0000000..a024035 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-f16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5871e7ea39d07f68d149d45199ab773aad3a32a95b05d9e4b6df1d0994c2711c +size 1504818112 diff --git a/granite-3.1-1b-a400m-instruct-iq3_m.gguf b/granite-3.1-1b-a400m-instruct-iq3_m.gguf new file mode 100644 index 0000000..d8f311d --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-iq3_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66bfd74e055f9394fef43183f5ba505e48331efb6ebb6cd89022a60d29097ab5 +size 593192256 diff --git a/granite-3.1-1b-a400m-instruct-iq3_s.gguf b/granite-3.1-1b-a400m-instruct-iq3_s.gguf new file mode 100644 index 0000000..90b2aca --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-iq3_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d2d06315e5cb59489ae9e431f78e3e79f2df98eb8ebfcb3f645bce088a85d5d +size 593192256 diff --git a/granite-3.1-1b-a400m-instruct-iq3_xs.gguf b/granite-3.1-1b-a400m-instruct-iq3_xs.gguf new file mode 100644 index 0000000..d8757fc --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-iq3_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6d7f12e5ccf3fd410f570b586ca59753bb27d9488c47657079578ae7407c6fa +size 561415488 diff --git a/granite-3.1-1b-a400m-instruct-iq3_xxs.gguf b/granite-3.1-1b-a400m-instruct-iq3_xxs.gguf new file mode 100644 index 0000000..fb2e3de --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-iq3_xxs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02b03ee2ad1cfe5f9ad3d1df97cb491e67b1a4845f8ccd6145b8631863d87e39 +size 544900416 diff --git a/granite-3.1-1b-a400m-instruct-iq4_nl.gguf b/granite-3.1-1b-a400m-instruct-iq4_nl.gguf new file mode 100644 index 0000000..5ae7dca --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-iq4_nl.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36d80cd4a866aac14b11bf6311e04bdb8d9ff3b749e5bd092a68344bd0994e7d +size 768321248 diff --git a/granite-3.1-1b-a400m-instruct-iq4_xs.gguf b/granite-3.1-1b-a400m-instruct-iq4_xs.gguf new file mode 100644 index 0000000..606aa79 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-iq4_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77d5db1d2934fecbe0c2a76fbf13969556e5a73d3417ba44048d08358c86eb2a +size 728213216 diff --git a/granite-3.1-1b-a400m-instruct-q3_k_m.gguf b/granite-3.1-1b-a400m-instruct-q3_k_m.gguf new file mode 100644 index 0000000..60ca5ef --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:395787e6c29c8313411bc8db2f71d9cc5f17c188b5a4b17a332ea18e9207d69d +size 673064672 diff --git a/granite-3.1-1b-a400m-instruct-q3_k_s.gguf b/granite-3.1-1b-a400m-instruct-q3_k_s.gguf new file mode 100644 index 0000000..0a692e8 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52ad8b2d5cd67ed72b24e6d5f8c35ae3c71463aab620c1e7129c6bd7cdc8ec5f +size 626271552 diff --git a/granite-3.1-1b-a400m-instruct-q4_0.gguf b/granite-3.1-1b-a400m-instruct-q4_0.gguf new file mode 100644 index 0000000..9e6f9c8 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c49de526bf4ccf59383ae0843533b0ef092383a3a11de2eb274e8e1abac468f8 +size 755344320 diff --git a/granite-3.1-1b-a400m-instruct-q4_1.gguf b/granite-3.1-1b-a400m-instruct-q4_1.gguf new file mode 100644 index 0000000..c1c7c1c --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b63ce8e01479f9ef200b4f9d332f414291947d7b1766a2689d9e2ae0ce795268 +size 838706304 diff --git a/granite-3.1-1b-a400m-instruct-q5_0.gguf b/granite-3.1-1b-a400m-instruct-q5_0.gguf new file mode 100644 index 0000000..d93fe41 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780dd1035742cee8183278edb11bce62879744f333b9119f15c79fcc4d10dfcb +size 922068288 diff --git a/granite-3.1-1b-a400m-instruct-q5_1.gguf b/granite-3.1-1b-a400m-instruct-q5_1.gguf new file mode 100644 index 0000000..18c3ea6 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a083ce4d8969217c5731cc5a78dc7e00b00b995b2c36a3ae47c0203640f4429 +size 1005430272 diff --git a/granite-3.1-1b-a400m-instruct-q5_k_m.gguf b/granite-3.1-1b-a400m-instruct-q5_k_m.gguf new file mode 100644 index 0000000..b61d701 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec1b432c542af1ad38b0891822c8d5b7aadbae428aea74b23009a6eb92cd62c1 +size 983901920 diff --git a/granite-3.1-1b-a400m-instruct-q5_k_s.gguf b/granite-3.1-1b-a400m-instruct-q5_k_s.gguf new file mode 100644 index 0000000..5dc481b --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6edddd29ad74ef772515b814a1ba8a7ede317535dea80a75def16257e4f061be +size 970114784 diff --git a/granite-3.1-1b-a400m-instruct-q6_k_m.gguf b/granite-3.1-1b-a400m-instruct-q6_k_m.gguf new file mode 100644 index 0000000..e920db0 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-q6_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e28408b3fcdee206103acadfed9dda3afc96cd1dfe66e4a947efb8e71694ce9c +size 1099212512 diff --git a/granite-3.1-1b-a400m-instruct-q8_0.gguf b/granite-3.1-1b-a400m-instruct-q8_0.gguf new file mode 100644 index 0000000..60f52e3 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8e7faba64b8161e45ec21f117f3ecdac6b6babfa006fc48e1f9d6233a0815ae +size 1422239872 diff --git a/granite-3.1-1b-a400m-instruct.imatrix b/granite-3.1-1b-a400m-instruct.imatrix new file mode 100644 index 0000000..56dc1b1 --- /dev/null +++ b/granite-3.1-1b-a400m-instruct.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d39a7c6f9b4977659adfd7be76dddf6d267bcee64dad5c51c2ab3605c8d804fb +size 8362672