From 24f8301f95e6fd584841439a1bfa1876a7306bec Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 25 Sep 2026 14:00:18 +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-4.0-h-1b-GGUF Source: Original Platform --- .gitattributes | 54 +++ README.md | 683 +++++++++++++++++++++++++++++++++ granite-4.0-h-1b-bf16.gguf | 3 + granite-4.0-h-1b-f16_q8_0.gguf | 3 + granite-4.0-h-1b-imatrix.gguf | 3 + granite-4.0-h-1b-iq3_m.gguf | 3 + granite-4.0-h-1b-iq3_xs.gguf | 3 + granite-4.0-h-1b-iq3_xxs.gguf | 3 + granite-4.0-h-1b-iq4_nl.gguf | 3 + granite-4.0-h-1b-iq4_xs.gguf | 3 + granite-4.0-h-1b-q3_k_m.gguf | 3 + granite-4.0-h-1b-q3_k_s.gguf | 3 + granite-4.0-h-1b-q4_0.gguf | 3 + granite-4.0-h-1b-q4_1.gguf | 3 + granite-4.0-h-1b-q4_k_m.gguf | 3 + granite-4.0-h-1b-q4_k_s.gguf | 3 + granite-4.0-h-1b-q5_0.gguf | 3 + granite-4.0-h-1b-q5_1.gguf | 3 + granite-4.0-h-1b-q5_k_m.gguf | 3 + granite-4.0-h-1b-q6_k_m.gguf | 3 + granite-4.0-h-1b-q8_0.gguf | 3 + 21 files changed, 794 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 granite-4.0-h-1b-bf16.gguf create mode 100644 granite-4.0-h-1b-f16_q8_0.gguf create mode 100644 granite-4.0-h-1b-imatrix.gguf create mode 100644 granite-4.0-h-1b-iq3_m.gguf create mode 100644 granite-4.0-h-1b-iq3_xs.gguf create mode 100644 granite-4.0-h-1b-iq3_xxs.gguf create mode 100644 granite-4.0-h-1b-iq4_nl.gguf create mode 100644 granite-4.0-h-1b-iq4_xs.gguf create mode 100644 granite-4.0-h-1b-q3_k_m.gguf create mode 100644 granite-4.0-h-1b-q3_k_s.gguf create mode 100644 granite-4.0-h-1b-q4_0.gguf create mode 100644 granite-4.0-h-1b-q4_1.gguf create mode 100644 granite-4.0-h-1b-q4_k_m.gguf create mode 100644 granite-4.0-h-1b-q4_k_s.gguf create mode 100644 granite-4.0-h-1b-q5_0.gguf create mode 100644 granite-4.0-h-1b-q5_1.gguf create mode 100644 granite-4.0-h-1b-q5_k_m.gguf create mode 100644 granite-4.0-h-1b-q6_k_m.gguf create mode 100644 granite-4.0-h-1b-q8_0.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d75afd8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.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-4.0-h-1b-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-q4_1.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-q5_1.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-h-1b-bf16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b23f08f --- /dev/null +++ b/README.md @@ -0,0 +1,683 @@ +--- +license: apache-2.0 +library_name: transformers +tags: +- language +- granite-4.0 +base_model: +- ibm-granite/granite-4.0-h-1b-base +--- + +# granite-4.0-h-1b GGUF Models + + +## Model Generation Details + +This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`16724b5b6`](https://github.com/ggerganov/llama.cpp/commit/16724b5b6836a2d4b8936a5824d2ff27c52b4517). + + + + + + +--- + + + Click here to get info on choosing the right GGUF model format + + +--- + + + + + + +# Granite-4.0-H-1B + +**Model Summary:** +Granite-4.0-H-1B is a lightweight instruct model finetuned from *Granite-4.0-H-1B-Base* using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. This model is developed using a diverse set of techniques including supervised finetuning, reinforcement learning, and model merging. + +- **Developers:** Granite Team, IBM +- **HF Collection:** [Granite 4.0 Nano Language Models HF Collection](https://huggingface.co/collections/ibm-granite/granite-40-nano-language-models-68e5775c80b60e43b72cfa16) +- **GitHub Repository:** [ibm-granite/granite-4.0-nano-language-models](https://github.com/ibm-granite/granite-4.0-nano-language-models) +- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/) +- **Release Date**: October 28, 2025 +- **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 fine-tune Granite 4.0 Nano models to support languages beyond those included in this list. + +**Intended use:** +Granite 4.0 Nano instruct models feature strong instruction following capabilities bringing advanced AI capabilities within reach for on-device deployments and research use cases. Additionally, their compact size makes them well-suited for fine-tuning on specialized domains without requiring massive compute resources. + +*Capabilities* +* Summarization +* Text classification +* Text extraction +* Question-answering +* Retrieval Augmented Generation (RAG) +* Code related tasks +* Function-calling tasks +* Multilingual dialog use cases +* Fill-In-the-Middle (FIM) code completions + + + +**Generation:** +This is a simple example of how to use Granite-4.0-H-1B 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 = "cuda" +model_path = "ibm-granite/granite-4.0-h-1b" +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[0]) +``` + +Expected output: +```shell +<|start_of_role|>user<|end_of_role|>Please list one IBM Research laboratory located in the United States. You should only output its name and location.<|end_of_text|> +<|start_of_role|>assistant<|end_of_role|>Almaden Research Center, San Jose, California<|end_of_text|> +``` + +**Tool-calling:** +Granite-4.0-H-1B comes with enhanced tool calling capabilities, enabling seamless integration with external functions and APIs. To define a list of tools please follow OpenAI's function [definition schema](https://platform.openai.com/docs/guides/function-calling?api-mode=responses#defining-functions). + +This is an example of how to use Granite-4.0-H-1B model tool-calling ability: + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +device = "cuda" +model_path = "ibm-granite/granite-4.0-h-1b" +tokenizer = AutoTokenizer.from_pretrained(model_path) +# drop device_map if running on CPU +model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device) +model.eval() + +tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather for a specified city.", + "parameters": { + "type": "object", + "properties": { + "city": { + "type": "string", + "description": "Name of the city" + } + }, + "required": ["city"] + } + } + } +] + +# change input text as desired +chat = [ + { "role": "user", "content": "What's the weather like in Boston right now?" }, +] +chat = tokenizer.apply_chat_template(chat, \ + tokenize=False, \ + tools=tools, \ + 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[0]) +``` + +Expected output: +```shell +<|start_of_role|>system<|end_of_role|>You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query. + +You are provided with function signatures within XML tags: + +{"type": "function", "function": {"name": "get_current_weather", "description": "Get the current weather for a specified city.", "parameters": {"type": "object", "properties": {"city": {"type": "string", "description": "Name of the city"}}, "required": ["city"]}}} + + +For each tool call, return a json object with function name and arguments within XML tags: + +{"name": , "arguments": } +. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.<|end_of_text|> +<|start_of_role|>user<|end_of_role|>What's the weather like in Boston right now?<|end_of_text|> +<|start_of_role|>assistant<|end_of_role|> +{"name": "get_current_weather", "arguments": {"city": "Boston"}} +<|end_of_text|> +``` + + + +**Evaluation Results:** + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
BenchmarksMetric350M DenseH 350M Dense1B DenseH 1B Dense
+ General Tasks +
MMLU5-shot35.0136.2159.3959.74
MMLU-Pro5-shot, CoT12.1314.3834.0232.86
BBH3-shot, CoT33.0733.2860.3759.68
AGI EVAL0-shot, CoT26.2229.6149.2252.44
GPQA0-shot, CoT24.1126.1229.9129.69
+ Alignment Tasks +
IFEvalInstruct, Strict61.6367.6380.8282.37
IFEvalPrompt, Strict49.1755.6473.9474.68
IFEvalAverage55.461.6377.3878.53
+ Math Tasks +
GSM8K8-shot30.7139.2776.3569.83
GSM Symbolic8-shot26.7633.772.365.72
Minerva Math0-shot, CoT13.045.7645.2849.4
DeepMind Math0-shot, CoT8.456.23434.98
+ Code Tasks +
HumanEvalpass@139387473
HumanEval+pass@137356968
MBPPpass@148496569
MBPP+pass@138445760
CRUXEval-Opass@123.7525.533.1336
BigCodeBenchpass@111.1411.2330.1829.12
+ Tool Calling Tasks +
BFCL v339.3243.3254.8250.21
+ Multilingual Tasks +
MULTIPLEpass@115.9914.3132.2436.11
MMMLU5-shot28.2327.954549.43
INCLUDE5-shot27.7427.0942.1243.35
MGSM8-shot14.7216.1637.8427.52
+ Safety +
SALAD-Bench97.1296.5593.4496.4
AttaQ82.5381.7685.2682.85
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Multilingual Benchmarks and thr included languages:
Benchmarks# LangsLanguages
MMMLU11ar, de, en, es, fr, ja, ko, pt, zh, bn, hi
INCLUDE14hi, bn, ta, te, ar, de, es, fr, it, ja, ko, nl, pt, zh
MGSM5en, es, fr, ja, zh
+ +**Model Architecture:** + +Granite-4.0-H-1B baseline is based on a decoder-only dense transformer architecture. Core components of this architecture are: GQA, Mamba2, MLP with SwiGLU, RMSNorm, and shared input/output embeddings. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Model350M DenseH 350M Dense1B DenseH 1B Dense
Embedding size102476820481536
Number of layers28 attention4 attention / 28 Mamba240 attention4 attention / 36 Mamba2
Attention head size6464128128
Number of attention heads16121612
Number of KV heads4444
Mamba2 state size-128-128
Number of Mamba2 heads-48-48
MLP / Shared expert hidden size2048204840964096
Num. Experts----
Num. active Experts----
Expert hidden size----
MLP activationSwiGLUSwiGLUSwiGLUSwiGLU
Sequence length32K32K128K128K
Position embeddingRoPENoPERoPENoPE
# Parameters350M340M1.6B1.5B
# Active parameters350M340M1.6B1.5B
+ +**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, and (3) a select set of human-curated data. + +**Infrastructure:** +We trained the Granite 4.0 Nano Language Models utilizing an NVIDIA GB200 NVL72 cluster hosted in CoreWeave. Intra-rack communication occurs via the 72-GPU NVLink domain, and a non-blocking, full Fat-Tree NDR 400 Gb/s InfiniBand network provides inter-rack communication. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs. + +**Ethical Considerations and Limitations:** +Granite 4.0 Nano Instruct Models are primarily finetuned using instruction-response pairs mostly in English, but also multilingual data covering multiple 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 +- πŸ“„ Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/ +- πŸ’‘ Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources + + + + + +--- + +# πŸš€ If you find these models useful + +Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**: + +πŸ‘‰ [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) + +πŸ’¬ **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): +- βœ… **Zero-configuration setup** +- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low. +- πŸ”§ **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) + +πŸ”΅ **HugLLM** – Latest Open-source models: +- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita. + +### πŸ’‘ **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 OpenAIβ€”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) β˜•. 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-4.0-h-1b-bf16.gguf b/granite-4.0-h-1b-bf16.gguf new file mode 100644 index 0000000..787ce97 --- /dev/null +++ b/granite-4.0-h-1b-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56728d6e8d839bc1699ab0957588140141771ea04647e6fdebf04f57b8ecd181 +size 2928332416 diff --git a/granite-4.0-h-1b-f16_q8_0.gguf b/granite-4.0-h-1b-f16_q8_0.gguf new file mode 100644 index 0000000..e5fd29f --- /dev/null +++ b/granite-4.0-h-1b-f16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3601b95f173429725adc8c0ab911dd2dde3edbc6ca843b8df98276b05fd7073c +size 1951159648 diff --git a/granite-4.0-h-1b-imatrix.gguf b/granite-4.0-h-1b-imatrix.gguf new file mode 100644 index 0000000..e3762e4 --- /dev/null +++ b/granite-4.0-h-1b-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07b8ef8a3e5eb1d4d8cdf092e6995fb4a8be6a317c9be3d75a684915cdd20d91 +size 1940736 diff --git a/granite-4.0-h-1b-iq3_m.gguf b/granite-4.0-h-1b-iq3_m.gguf new file mode 100644 index 0000000..63b1c62 --- /dev/null +++ b/granite-4.0-h-1b-iq3_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:440bdad29efe23a6b750cc2a62c450ed21cff0263de5278a26b285810a2b1373 +size 722240928 diff --git a/granite-4.0-h-1b-iq3_xs.gguf b/granite-4.0-h-1b-iq3_xs.gguf new file mode 100644 index 0000000..889f216 --- /dev/null +++ b/granite-4.0-h-1b-iq3_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c59edfe6e717d9d9a629e5bf8a1a4141c675c2dac6b27ed3fc9c4c46bc41104 +size 681616800 diff --git a/granite-4.0-h-1b-iq3_xxs.gguf b/granite-4.0-h-1b-iq3_xxs.gguf new file mode 100644 index 0000000..ead46d9 --- /dev/null +++ b/granite-4.0-h-1b-iq3_xxs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c2c28ac850a03ad6fcbd26f1a01b2f5f12882f37790ecce48e22707725062e0 +size 650256288 diff --git a/granite-4.0-h-1b-iq4_nl.gguf b/granite-4.0-h-1b-iq4_nl.gguf new file mode 100644 index 0000000..a38ef71 --- /dev/null +++ b/granite-4.0-h-1b-iq4_nl.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c9833d70003312371fa133c740cd03f5112f72e1446b2072b056fe4dfdd283 +size 828577440 diff --git a/granite-4.0-h-1b-iq4_xs.gguf b/granite-4.0-h-1b-iq4_xs.gguf new file mode 100644 index 0000000..2b29536 --- /dev/null +++ b/granite-4.0-h-1b-iq4_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c82709e1fa5714f5f678880c776ff7942a3c42f8b35fafdad20a3ff2023d3467 +size 827486880 diff --git a/granite-4.0-h-1b-q3_k_m.gguf b/granite-4.0-h-1b-q3_k_m.gguf new file mode 100644 index 0000000..2c78356 --- /dev/null +++ b/granite-4.0-h-1b-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5848c07dc519fe6f5666751358541c7e7dba6a3b74c3432389723d0888f9a4dc +size 729589152 diff --git a/granite-4.0-h-1b-q3_k_s.gguf b/granite-4.0-h-1b-q3_k_s.gguf new file mode 100644 index 0000000..24ba586 --- /dev/null +++ b/granite-4.0-h-1b-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdd6fc1ffba2acce0a7a611851bf11e0008f19b39af6a96e2bfeace97341f7b8 +size 709117344 diff --git a/granite-4.0-h-1b-q4_0.gguf b/granite-4.0-h-1b-q4_0.gguf new file mode 100644 index 0000000..9f8f51b --- /dev/null +++ b/granite-4.0-h-1b-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5a4fd1879f05d470d6a3f5a2dde0cf65e3ec40a4491013601dbc6db79305207 +size 905647776 diff --git a/granite-4.0-h-1b-q4_1.gguf b/granite-4.0-h-1b-q4_1.gguf new file mode 100644 index 0000000..9d355e1 --- /dev/null +++ b/granite-4.0-h-1b-q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54b3aa921a26432998b83df5814672d87d698ebb5905caf203ef64771c6a9c64 +size 929504928 diff --git a/granite-4.0-h-1b-q4_k_m.gguf b/granite-4.0-h-1b-q4_k_m.gguf new file mode 100644 index 0000000..3885bf2 --- /dev/null +++ b/granite-4.0-h-1b-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ec12997734555aa15f084bf05bfdad29caccba293fb340462a6f6a05536f3f1 +size 931808928 diff --git a/granite-4.0-h-1b-q4_k_s.gguf b/granite-4.0-h-1b-q4_k_s.gguf new file mode 100644 index 0000000..69105f6 --- /dev/null +++ b/granite-4.0-h-1b-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3fc2e4d441ef04b7b847ed9f2b9e865da795035a4e42624e01f97e8b95b6136 +size 875787936 diff --git a/granite-4.0-h-1b-q5_0.gguf b/granite-4.0-h-1b-q5_0.gguf new file mode 100644 index 0000000..1710a50 --- /dev/null +++ b/granite-4.0-h-1b-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109d5f9d56fb74fe628b5431bb2cbfa4aefafccf19eb0f1c930ec32b74c2000c +size 1068967584 diff --git a/granite-4.0-h-1b-q5_1.gguf b/granite-4.0-h-1b-q5_1.gguf new file mode 100644 index 0000000..cee0556 --- /dev/null +++ b/granite-4.0-h-1b-q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:543cb0601f50a076ae9592b8ababc62336b3d733f2373bb8dc46a380f006ae71 +size 1150627488 diff --git a/granite-4.0-h-1b-q5_k_m.gguf b/granite-4.0-h-1b-q5_k_m.gguf new file mode 100644 index 0000000..3721d75 --- /dev/null +++ b/granite-4.0-h-1b-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b3b5005860e4b73fbebf32ac80bd10407994324bd3d9ba903c12b4576251f28 +size 1085888160 diff --git a/granite-4.0-h-1b-q6_k_m.gguf b/granite-4.0-h-1b-q6_k_m.gguf new file mode 100644 index 0000000..91c7448 --- /dev/null +++ b/granite-4.0-h-1b-q6_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:462a6e0d09056e9461210a7f4f6a65be7721d2a3e0d460b78068db767569953e +size 1242494880 diff --git a/granite-4.0-h-1b-q8_0.gguf b/granite-4.0-h-1b-q8_0.gguf new file mode 100644 index 0000000..50427f0 --- /dev/null +++ b/granite-4.0-h-1b-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8aef68d57e00751a439c309d4bf8515184133cfeb727e7455463b899f4cbdb3 +size 1558926688