GGUF
Merge
TIES
Llama3
BestMix
Chemistry
Einstein
instruction-following
conversational
long-form-generation
scientific
Instructions to use QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M
Use Docker
docker model run hf.co/QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF with Ollama:
ollama run hf.co/QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M
- Unsloth Studio
How to use QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF to start chatting
- Docker Model Runner
How to use QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF with Docker Model Runner:
docker model run hf.co/QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M
- Lemonade
How to use QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Llama3.1-BestMix-Chem-Einstein-8B-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- merge
|
| 7 |
+
- TIES
|
| 8 |
+
- Llama3
|
| 9 |
+
- BestMix
|
| 10 |
+
- Chemistry
|
| 11 |
+
- Einstein
|
| 12 |
+
- instruction-following
|
| 13 |
+
- conversational
|
| 14 |
+
- long-form-generation
|
| 15 |
+
- scientific
|
| 16 |
+
base_model:
|
| 17 |
+
- bunnycore/Best-Mix-Llama-3.1-8B
|
| 18 |
+
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
[](https://hf.co/QuantFactory)
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
# QuantFactory/Llama3.1-BestMix-Chem-Einstein-8B-GGUF
|
| 25 |
+
This is quantized version of [ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B](https://huggingface.co/ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B) created using llama.cpp
|
| 26 |
+
|
| 27 |
+
# Original Model Card
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
# **ZeroXClem/Llama3.1-BestMix-Chem-Einstein-8B**
|
| 32 |
+
|
| 33 |
+
**Llama3.1-BestMix-Chem-Einstein-8B** is an innovative, meticulously blended model designed to excel in **instruction-following**, **chemistry-focused tasks**, and **long-form conversational generation**. This model fuses the **best qualities** of multiple Llama3-based architectures, making it highly versatile for both general and specialized tasks. π»π§ β¨
|
| 34 |
+
|
| 35 |
+
## π **Family Tree**
|
| 36 |
+
|
| 37 |
+
This model is the result of merging the following:
|
| 38 |
+
|
| 39 |
+
- [**bunnycore/Best-Mix-Llama-3.1-8B**](https://huggingface.co/bunnycore/Best-Mix-Llama-3.1-8B): A balanced blend of top Llama models, optimized for general performance across reasoning, instruction-following, and math.
|
| 40 |
+
- [**USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B**](https://huggingface.co/USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B): A model specialized in **scientific knowledge** and **chemistry**, excelling in chemistry benchmarks.
|
| 41 |
+
- [**Weyaxi/Einstein-v6.1-Llama3-8B**](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B): Fine-tuned for **long-form generation**, **conversation-heavy tasks**, and optimized with cutting-edge techniques for efficient memory usage and fast performance.
|
| 42 |
+
|
| 43 |
+
---
|
| 44 |
+
|
| 45 |
+
## 𧬠**Model Lineage**
|
| 46 |
+
|
| 47 |
+
### **A: bunnycore/Best-Mix-Llama-3.1-8B**
|
| 48 |
+
|
| 49 |
+
- A masterful **blend** of several Llama3 models like **Aurora_faustus**, **TitanFusion**, and **OpenMath2**.
|
| 50 |
+
- Provides a **balanced performance** in a variety of tasks such as reasoning, math, and instruction-following.
|
| 51 |
+
- Key contributor to the **overall versatility** of the merged model.
|
| 52 |
+
|
| 53 |
+
### **B: USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B**
|
| 54 |
+
|
| 55 |
+
- Specializes in **chemistry** and **scientific knowledge**, outperforming many larger models in **chemistry benchmarks**.
|
| 56 |
+
- Adds **scientific rigor** and domain-specific expertise to the merged model, making it perfect for scientific and academic tasks.
|
| 57 |
+
|
| 58 |
+
### **C: Weyaxi/Einstein-v6.1-Llama3-8B**
|
| 59 |
+
|
| 60 |
+
- Fine-tuned on a wide range of **instructive** and **conversational datasets** like **WizardLM**, **Alpaca**, and **ShareGPT**.
|
| 61 |
+
- Optimized for **long-form text generation** and enhanced with **xformers attention** and **flash attention** techniques for better performance.
|
| 62 |
+
- Key player in **dialogue-based tasks** and **long conversation generation**.
|
| 63 |
+
|
| 64 |
+
---
|
| 65 |
+
|
| 66 |
+
## π οΈ **Merge Details**
|
| 67 |
+
|
| 68 |
+
This model was merged using the **TIES merge method**, ensuring a smooth integration of the key strengths from each contributing model. Here's the configuration used:
|
| 69 |
+
|
| 70 |
+
```yaml
|
| 71 |
+
yaml
|
| 72 |
+
Copy code
|
| 73 |
+
models:
|
| 74 |
+
- model: bunnycore/Best-Mix-Llama-3.1-8B
|
| 75 |
+
parameters:
|
| 76 |
+
density: [1, 0.7, 0.5]
|
| 77 |
+
weight: 1.0
|
| 78 |
+
|
| 79 |
+
- model: USTC-KnowledgeComputingLab/Llama3-KALE-LM-Chem-1.5-8B
|
| 80 |
+
parameters:
|
| 81 |
+
density: 0.6
|
| 82 |
+
weight: [0.3, 0.7, 1.0]
|
| 83 |
+
|
| 84 |
+
- model: Weyaxi/Einstein-v6.1-Llama3-8B
|
| 85 |
+
parameters:
|
| 86 |
+
density: 0.4
|
| 87 |
+
weight:
|
| 88 |
+
- filter: mlp
|
| 89 |
+
value: 0.5
|
| 90 |
+
- filter: self_attn
|
| 91 |
+
value: 0.7
|
| 92 |
+
- value: 0.5
|
| 93 |
+
|
| 94 |
+
merge_method: ties
|
| 95 |
+
base_model: bunnycore/Best-Mix-Llama-3.1-8B
|
| 96 |
+
parameters:
|
| 97 |
+
normalize: true
|
| 98 |
+
int8_mask: true
|
| 99 |
+
dtype: float16
|
| 100 |
+
|
| 101 |
+
```
|
| 102 |
+
|
| 103 |
+
---
|
| 104 |
+
|
| 105 |
+
## π― **Key Features & Capabilities**
|
| 106 |
+
|
| 107 |
+
### **1. Instruction Following & General Reasoning**:
|
| 108 |
+
|
| 109 |
+
With the foundation of **Best-Mix**, this model excels in **general-purpose reasoning**, instruction-following, and tasks that require high adaptability.
|
| 110 |
+
|
| 111 |
+
### **2. Scientific & Chemistry Expertise**:
|
| 112 |
+
|
| 113 |
+
Thanks to the contribution from **KALE-LM-Chem**, this model shines in **scientific research**, particularly **chemistry-focused tasks**, making it ideal for academic and research purposes.
|
| 114 |
+
|
| 115 |
+
### **3. Long-Form & Conversational Mastery**:
|
| 116 |
+
|
| 117 |
+
With **Einstein-v6.1**, the model handles **long-form generation** effortlessly, excelling in extended conversations and structured dialogue applications.
|
| 118 |
+
|
| 119 |
+
---
|
| 120 |
+
|
| 121 |
+
## π **Performance Benchmarks**
|
| 122 |
+
|
| 123 |
+
While still in its early stages, **Llama3.1-BestMix-Chem-Einstein-8B** is expected to perform well across a variety of benchmarks, including:
|
| 124 |
+
|
| 125 |
+
- **Chemistry-focused benchmarks** (KALE-LM-Chem)
|
| 126 |
+
- **Instruction-following tasks** (Best-Mix)
|
| 127 |
+
- **Conversational AI** and **long-form text generation** (Einstein-v6.1)
|
| 128 |
+
|
| 129 |
+
Further testing and evaluation will continue to refine this model's capabilities.
|
| 130 |
+
|
| 131 |
+
---
|
| 132 |
+
|
| 133 |
+
## π **License**
|
| 134 |
+
|
| 135 |
+
This model is open-sourced under the **Apache-2.0 License**, allowing free use and modification with proper attribution.
|
| 136 |
+
|
| 137 |
+
---
|
| 138 |
+
|
| 139 |
+
## π‘ **Tags**
|
| 140 |
+
|
| 141 |
+
- `merge`
|
| 142 |
+
- `TIES`
|
| 143 |
+
- `BestMix`
|
| 144 |
+
- `Chemistry`
|
| 145 |
+
- `Einstein`
|
| 146 |
+
- `instruction-following`
|
| 147 |
+
- `long-form-generation`
|
| 148 |
+
- `conversational`
|
| 149 |
+
|
| 150 |
+
---
|