初始化项目，由ModelHub XC社区提供模型
Model: Mungert/granite-3.0-2b-base-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
70
.gitattributes
vendored
Normal file
70
.gitattributes
vendored
Normal file
@@ -0,0 +1,70 @@
|
||||
*.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-3.0-2b-base-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base.imatrix filter=lfs diff=lfs merge=lfs -text
|
||||
granite-3.0-2b-base-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
391
README.md
Normal file
391
README.md
Normal file
@@ -0,0 +1,391 @@
|
||||
---
|
||||
pipeline_tag: text-generation
|
||||
inference: false
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
tags:
|
||||
- language
|
||||
- granite-3.0
|
||||
model-index:
|
||||
- name: granite-3.0-2b-base
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: human-exams
|
||||
name: MMLU
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 55
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: human-exams
|
||||
name: MMLU-Pro
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 23.79
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: human-exams
|
||||
name: AGI-Eval
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 22.56
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: commonsense
|
||||
name: WinoGrande
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 74.9
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: commonsense
|
||||
name: OBQA
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 43
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: commonsense
|
||||
name: SIQA
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 59.84
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: commonsense
|
||||
name: PIQA
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 79.27
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: commonsense
|
||||
name: Hellaswag
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 77.65
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: commonsense
|
||||
name: TruthfulQA
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 39.9
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: reading-comprehension
|
||||
name: BoolQ
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 81.35
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: reading-comprehension
|
||||
name: SQuAD 2.0
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 25.22
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: reasoning
|
||||
name: ARC-C
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 54.27
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: reasoning
|
||||
name: GPQA
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 30.58
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: reasoning
|
||||
name: BBH
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 40.69
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: reasoning
|
||||
name: MUSR
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 34.34
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: code
|
||||
name: HumanEval
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 38.41
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: code
|
||||
name: MBPP
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 35.4
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: math
|
||||
name: GSM8K
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 47.23
|
||||
veriefied: false
|
||||
- task:
|
||||
type: text-generation
|
||||
dataset:
|
||||
type: math
|
||||
name: MATH
|
||||
metrics:
|
||||
- name: pass@1
|
||||
type: pass@1
|
||||
value: 19.46
|
||||
veriefied: false
|
||||
new_version: ibm-granite/granite-3.1-2b-base
|
||||
---
|
||||
|
||||
# <span style="color: #7FFF7F;">granite-3.0-2b-base GGUF Models</span>
|
||||
|
||||
|
||||
## <span style="color: #7F7FFF;">Model Generation Details</span>
|
||||
|
||||
This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`5dd942de`](https://github.com/ggerganov/llama.cpp/commit/5dd942de5922a22ec8446a4ad2203738dbcb9389).
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
---
|
||||
|
||||
<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;">
|
||||
Click here to get info on choosing the right GGUF model format
|
||||
</a>
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
<!--Begin Original Model Card-->
|
||||
|
||||
|
||||
<!--  -->
|
||||
|
||||
# Granite-3.0-2B-Base
|
||||
|
||||
**Model Summary:**
|
||||
Granite-3.0-2B-Base is a decoder-only language model to support a variety of text-to-text generation tasks. It is trained from scratch following a two-stage training strategy. In the first stage, it is trained on 10 trillion tokens sourced from diverse domains. During the second stage, it is further trained on 2 trillion tokens using a carefully curated mix of high-quality data, aiming to enhance its performance on specific tasks.
|
||||
|
||||
- **Developers:** Granite Team, IBM
|
||||
- **GitHub Repository:** [ibm-granite/granite-3.0-language-models](https://github.com/ibm-granite/granite-3.0-language-models)
|
||||
- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/)
|
||||
- **Paper:** [Granite 3.0 Language Models](https://github.com/ibm-granite/granite-3.0-language-models/blob/main/paper.pdf)
|
||||
- **Release Date**: October 21st, 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 3.0 models for languages beyond these 12 languages.
|
||||
|
||||
**Intended use:**
|
||||
Prominent use cases of LLMs in text-to-text generation include summarization, text classification, extraction, question-answering, and more. All Granite Base models are able to handle these tasks as they were trained on a large amount of data from various domains. Moreover, they can serve as baseline to create specialized models for specific application scenarios.
|
||||
|
||||
**Generation:**
|
||||
This is a simple example of how to use Granite-3.0-2B-Base model.
|
||||
|
||||
Install the following libraries:
|
||||
|
||||
```shell
|
||||
pip install torch torchvision torchaudio
|
||||
pip install accelerate
|
||||
pip install transformers
|
||||
```
|
||||
Then, copy the code snippet below to run the example.
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
device = "auto"
|
||||
model_path = "ibm-granite/granite-3.0-2b-base"
|
||||
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
|
||||
input_text = "Where is the Thomas J. Watson Research Center located?"
|
||||
# tokenize the text
|
||||
input_tokens = tokenizer(input_text, return_tensors="pt").to(device)
|
||||
# generate output tokens
|
||||
output = model.generate(**input_tokens,
|
||||
max_length=4000)
|
||||
# decode output tokens into text
|
||||
output = tokenizer.batch_decode(output)
|
||||
# print output
|
||||
print(output)
|
||||
```
|
||||
|
||||
**Model Architecture:**
|
||||
Granite-3.0-2B-Base 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.
|
||||
|
||||
| Model | 2B Dense | 8B Dense | 1B MoE | 3B MoE |
|
||||
| :-------- | :-------- | :--------| :--------| :--------|
|
||||
| Embedding size | **2048** | 4096 | 1024 | 1536 |
|
||||
| Number of layers | **40** | 40 | 24 | 32 |
|
||||
| Attention head size | **64** | 128 | 64 | 64 |
|
||||
| Number of attention heads | **32** | 32 | 16 | 24 |
|
||||
| Number of KV heads | **8** | 8 | 8 | 8 |
|
||||
| MLP hidden size | **8192** | 12800 | 512 | 512 |
|
||||
| MLP activation | **SwiGLU** | SwiGLU | SwiGLU | SwiGLU |
|
||||
| Number of Experts | **—** | — | 32 | 40 |
|
||||
| MoE TopK | **—** | — | 8 | 8 |
|
||||
| Initialization std | **0.1** | 0.1 | 0.1 | 0.1 |
|
||||
| Sequence Length | **4096** | 4096 | 4096 | 4096 |
|
||||
| Position Embedding | **RoPE** | RoPE | RoPE | RoPE |
|
||||
| # Parameters | **2.5B** | 8.1B | 1.3B | 3.3B |
|
||||
| # Active Parameters | **2.5B** | 8.1B | 400M | 800M |
|
||||
| # Training tokens | **12T** | 12T | 10T | 10T |
|
||||
|
||||
**Training Data:**
|
||||
This model is trained on a mix of open source and proprietary data following a two-stage training strategy.
|
||||
* Stage 1 data: The data for stage 1 is sourced from diverse domains, such as: web, code, academic sources, books, and math data.
|
||||
* Stage 2 data: The data for stage 2 comprises a curated mix of high-quality data from the same domains, plus multilingual and instruction data. The goal of this second training phase is to enhance the model’s performance on specific tasks.
|
||||
|
||||
A detailed attribution of datasets can be found in the [Granite Technical Report](https://github.com/ibm-granite/granite-3.0-language-models/blob/main/paper.pdf) and [Accompanying Author List](https://github.com/ibm-granite/granite-3.0-language-models/blob/main/author-ack.pdf).
|
||||
|
||||
**Infrastructure:**
|
||||
We train Granite 3.0 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 while minimizing environmental impact by utilizing 100% renewable energy sources.
|
||||
|
||||
**Ethical Considerations and Limitations:**
|
||||
The use of Large Language Models involves risks and ethical considerations people must be aware of, including but not limited to: bias and fairness, misinformation, and autonomous decision-making. Granite-3.0-2B-Base model is not the exception in this regard. Even though this model is suited for multiple generative AI tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying text verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use Granite-3.0-2B-Base model with ethical intentions and in a responsible way.
|
||||
|
||||
**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
|
||||
|
||||
<!-- ## Citation
|
||||
```
|
||||
@misc{granite-models,
|
||||
author = {author 1, author2, ...},
|
||||
title = {},
|
||||
journal = {},
|
||||
volume = {},
|
||||
year = {2024},
|
||||
url = {https://arxiv.org/abs/0000.00000},
|
||||
}
|
||||
``` -->
|
||||
|
||||
<!--End Original Model Card-->
|
||||
|
||||
---
|
||||
|
||||
# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
|
||||
|
||||
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! 😊
|
||||
3
granite-3.0-2b-base-bf16.gguf
Normal file
3
granite-3.0-2b-base-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a8e4de12ac22730e1c732b999596e7cfcc4e6de67b5de67804a19706e489b41d
|
||||
size 5069124512
|
||||
3
granite-3.0-2b-base-bf16_q8_0.gguf
Normal file
3
granite-3.0-2b-base-bf16_q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d3f2edb95949a0dedd64a9fa5dd8ecdd8daa780b0156e92a94b6292fc8f75bb7
|
||||
size 3614225312
|
||||
3
granite-3.0-2b-base-f16_q8_0.gguf
Normal file
3
granite-3.0-2b-base-f16_q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5673f794356cf5db2da9750b9345d31747202ad4f8884c0b8b4fa2b136173b76
|
||||
size 3614225312
|
||||
3
granite-3.0-2b-base-iq3_m.gguf
Normal file
3
granite-3.0-2b-base-iq3_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:45e563baa46ebd31f19409b7e6d240989fcda3099327ff1a92ed8aa955c7aa19
|
||||
size 1197192416
|
||||
3
granite-3.0-2b-base-iq3_s.gguf
Normal file
3
granite-3.0-2b-base-iq3_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:210eab0d52626b3df01fab5dc3f9dd158abec9f3de6e51343cdeec653dfe552b
|
||||
size 1197192416
|
||||
3
granite-3.0-2b-base-iq3_xs.gguf
Normal file
3
granite-3.0-2b-base-iq3_xs.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:29b78ccef5f250adf88d5c60acaef3942ba839cbb113665dc36ad294ae69bd16
|
||||
size 1074377952
|
||||
3
granite-3.0-2b-base-iq3_xxs.gguf
Normal file
3
granite-3.0-2b-base-iq3_xxs.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b08f3cb38203358896b14b47dd6c56e12f38096521583848de8094e10980a7b0
|
||||
size 1045542112
|
||||
3
granite-3.0-2b-base-iq4_nl.gguf
Normal file
3
granite-3.0-2b-base-iq4_nl.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1b2724cc7ae7284b4c8ead141a7a2cf091579ea11aa04e81cf683b440cbcce84
|
||||
size 1458615520
|
||||
3
granite-3.0-2b-base-iq4_xs.gguf
Normal file
3
granite-3.0-2b-base-iq4_xs.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4a11ba4248797dd6d137d7c346502473146ce8a68b68e36f5e907cc8d5f81223
|
||||
size 1383904480
|
||||
3
granite-3.0-2b-base-q3_k_m.gguf
Normal file
3
granite-3.0-2b-base-q3_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e78de5b9d44bdaeca5f92990f7f7532a7559eceaa15fd13c02fa549894a32d38
|
||||
size 1243067616
|
||||
3
granite-3.0-2b-base-q3_k_s.gguf
Normal file
3
granite-3.0-2b-base-q3_k_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1dccb21d1c20dc15db70282b50225ca7e2c2c10c5ee1dbed0653fa6beac4b5f0
|
||||
size 1229698272
|
||||
3
granite-3.0-2b-base-q4_0.gguf
Normal file
3
granite-3.0-2b-base-q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:962159199e81fa3a094fb395953f1551523857eaa29e75ae2c9a6af93510e725
|
||||
size 1427420384
|
||||
3
granite-3.0-2b-base-q4_1.gguf
Normal file
3
granite-3.0-2b-base-q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cb80039cd0cda2569402999a1480ac33a75488889f664ed4f430acea8f0c7c7c
|
||||
size 1585755360
|
||||
3
granite-3.0-2b-base-q4_k_m.gguf
Normal file
3
granite-3.0-2b-base-q4_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3dc7bab07d5aece9351f84eb858b3bce10c32001c03c8c1b70e12b0bb77ad007
|
||||
size 1530541280
|
||||
3
granite-3.0-2b-base-q4_k_s.gguf
Normal file
3
granite-3.0-2b-base-q4_k_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:26b135204be79eed5480fd35a950a0d28bdace5c9636df77ec0b7745dd1e5c39
|
||||
size 1477489888
|
||||
3
granite-3.0-2b-base-q5_0.gguf
Normal file
3
granite-3.0-2b-base-q5_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b074eab52c56535eb022eee732e736c51a1f427a5e4241c3a962953d128fcbdd
|
||||
size 1744090336
|
||||
3
granite-3.0-2b-base-q5_1.gguf
Normal file
3
granite-3.0-2b-base-q5_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd66881ae89b4b12faac8c970f7edfa8e273945a97e906e3cbfe2a0b1c4afe87
|
||||
size 1902425312
|
||||
3
granite-3.0-2b-base-q5_k_m.gguf
Normal file
3
granite-3.0-2b-base-q5_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f3c5c84fdc16f3019c473c71af69c011c8c4744efee26ee2487d6966cfa0d5e0
|
||||
size 1809265888
|
||||
3
granite-3.0-2b-base-q5_k_s.gguf
Normal file
3
granite-3.0-2b-base-q5_k_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:01fac81425c1cda976ff1da0ed52aad51252c5b6448b568be417c061f09ecfc4
|
||||
size 1780856032
|
||||
3
granite-3.0-2b-base-q6_k_m.gguf
Normal file
3
granite-3.0-2b-base-q6_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c6d3f5feea74a3d93ff986203b46500b3ef75d172a10e77feeced3bd90d0a465
|
||||
size 2080552160
|
||||
3
granite-3.0-2b-base-q8_0.gguf
Normal file
3
granite-3.0-2b-base-q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:39b5c1a45cdccf39971838e484ac9b3647f918b706cbba349531f7c98949b83a
|
||||
size 2694099872
|
||||
3
granite-3.0-2b-base.imatrix
Normal file
3
granite-3.0-2b-base.imatrix
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4616cc746455791ce9af6c67fe18c48623fe2aa7c13920e672d1cc97714e6752
|
||||
size 3286132
|
||||
Reference in New Issue
Block a user