Downloads · 30 days
13
9% of all-time downloads
arcee-ai_-_arcee-lite-gguf
RichardErkhov/arcee-ai_-_arcee-lite-gguf
arcee-ai_-_arcee-lite-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
145
Public
Repo size
1.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf1.9 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 6, 2024
- Updated
- Aug 6, 2024
- SHA
- 14174df0
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
arcee-lite - GGUF
- Model creator: https://huggingface.co/arcee-ai/
- Original model: https://huggingface.co/arcee-ai/arcee-lite/
| Name | Quant method | Size |
|---|---|---|
| arcee-lite.Q2_K.gguf | Q2_K | 0.7GB |
| arcee-lite.IQ3_XS.gguf | IQ3_XS | 0.77GB |
| arcee-lite.IQ3_S.gguf | IQ3_S | 0.18GB |
| arcee-lite.Q3_K_S.gguf | Q3_K_S | 0.1GB |
| arcee-lite.IQ3_M.gguf | IQ3_M | 0.01GB |
| arcee-lite.Q3_K.gguf | Q3_K | 0.0GB |
| arcee-lite.Q3_K_M.gguf | Q3_K_M | 0.0GB |
| arcee-lite.Q3_K_L.gguf | Q3_K_L | 0.0GB |
| arcee-lite.IQ4_XS.gguf | IQ4_XS | 0.0GB |
| arcee-lite.Q4_0.gguf | Q4_0 | 0.0GB |
| arcee-lite.IQ4_NL.gguf | IQ4_NL | 0.0GB |
| arcee-lite.Q4_K_S.gguf | Q4_K_S | 0.0GB |
| arcee-lite.Q4_K.gguf | Q4_K | 0.0GB |
| arcee-lite.Q4_K_M.gguf | Q4_K_M | 0.0GB |
| arcee-lite.Q4_1.gguf | Q4_1 | 0.0GB |
| arcee-lite.Q5_0.gguf | Q5_0 | 0.0GB |
| arcee-lite.Q5_K_S.gguf | Q5_K_S | 0.0GB |
| arcee-lite.Q5_K.gguf | Q5_K | 0.0GB |
| arcee-lite.Q5_K_M.gguf | Q5_K_M | 0.0GB |
| arcee-lite.Q5_1.gguf | Q5_1 | 0.0GB |
| arcee-lite.Q6_K.gguf | Q6_K | 0.0GB |
| arcee-lite.Q8_0.gguf | Q8_0 | 0.0GB |
Original model description:
license: apache-2.0
<div align="center"> <img src="https://i.ibb.co/g9Z2CGQ/arcee-lite.webp" alt="Arcee-Lite" style="border-radius: 10px; box-shadow: 0 4px 8px 0 rgba(0, 0, 0, 0.2), 0 6px 20px 0 rgba(0, 0, 0, 0.19); max-width: 100%; height: auto;"> </div>Arcee-Lite is a compact yet powerful 1.5B parameter language model developed as part of the DistillKit open-source project. Despite its small size, Arcee-Lite demonstrates impressive performance, particularly in the MMLU (Massive Multitask Language Understanding) benchmark.
GGUFS available here
Key Features
- Model Size: 1.5 billion parameters
- MMLU Score: 55.93
- Distillation Source: Phi-3-Medium
- Enhanced Performance: Merged with high-performing distillations
About DistillKit
DistillKit is our new open-source project focused on creating efficient, smaller models that maintain high performance. Arcee-Lite is one of the first models to emerge from this initiative.
Performance
Arcee-Lite showcases remarkable capabilities for its size:
- Achieves a 55.93 score on the MMLU benchmark
- Demonstrates exceptional performance across various tasks
Use Cases
Arcee-Lite is suitable for a wide range of applications where a balance between model size and performance is crucial:
- Embedded systems
- Mobile applications
- Edge computing
- Resource-constrained environments
Please note that our internal evaluations were consistantly higher than their counterparts on the OpenLLM Leaderboard - and should only be compared against the relative performance between the models, not weighed against the leaderboard.
- Created
- Aug 6, 2024
- Updated
- Aug 6, 2024