Downloads · 30 days
88
7% of all-time downloads
arcee-ai_-_Llama-Spark-gguf
RichardErkhov/arcee-ai_-_Llama-Spark-gguf
arcee-ai_-_Llama-Spark-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
1.2K
Public
Repo size
92.9 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf108 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 10, 2024
- Updated
- Aug 10, 2024
- SHA
- a06651ae
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
Llama-Spark - GGUF
- Model creator: https://huggingface.co/arcee-ai/
- Original model: https://huggingface.co/arcee-ai/Llama-Spark/
| Name | Quant method | Size |
|---|---|---|
| Llama-Spark.Q2_K.gguf | Q2_K | 2.96GB |
| Llama-Spark.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| Llama-Spark.IQ3_S.gguf | IQ3_S | 3.43GB |
| Llama-Spark.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| Llama-Spark.IQ3_M.gguf | IQ3_M | 3.52GB |
| Llama-Spark.Q3_K.gguf | Q3_K | 3.74GB |
| Llama-Spark.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| Llama-Spark.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| Llama-Spark.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| Llama-Spark.Q4_0.gguf | Q4_0 | 4.34GB |
| Llama-Spark.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| Llama-Spark.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| Llama-Spark.Q4_K.gguf | Q4_K | 4.58GB |
| Llama-Spark.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| Llama-Spark.Q4_1.gguf | Q4_1 | 4.78GB |
| Llama-Spark.Q5_0.gguf | Q5_0 | 5.21GB |
| Llama-Spark.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| Llama-Spark.Q5_K.gguf | Q5_K | 5.34GB |
| Llama-Spark.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| Llama-Spark.Q5_1.gguf | Q5_1 | 5.65GB |
| Llama-Spark.Q6_K.gguf | Q6_K | 6.14GB |
| Llama-Spark.Q8_0.gguf | Q8_0 | 7.95GB |
Original model description:
license: llama3.1
<div align="center"> <img src="https://i.ibb.co/9hwFrvL/BLMs-Wkx-NQf-W-46-FZDg-ILhg.jpg" alt="Arcee Spark" 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>Llama-Spark is a powerful conversational AI model developed by Arcee.ai. It's built on the foundation of Llama-3.1-8B and merges the power of our Tome Dataset with Llama-3.1-8B-Instruct, resulting in a remarkable conversationalist that punches well above its 8B parameter weight class.
GGUFs available here
Model Description
Llama-Spark is our commitment to consistently delivering the best-performing conversational AI in the 6-9B parameter range. As new base models become available, we'll continue to update and improve Spark to maintain its leadership position.
This model is a successor to our original Arcee-Spark, incorporating advancements and learnings from our ongoing research and development.
Intended Uses
Llama-Spark is intended for use in conversational AI applications, such as chatbots, virtual assistants, and dialogue systems. It excels at engaging in natural and informative conversations.
Training Information
Llama-Spark is built upon the Llama-3.1-8B base model, fine-tuned using of the Tome Dataset and merged with Llama-3.1-8B-Instruct.
Evaluation Results
Please note that these scores are consistantly higher than the OpenLLM leaderboard, and should be compared to their relative performance increase not weighed against the leaderboard.
<div align="center"> <img src="https://i.ibb.co/pfSGLtB/Screenshot-2024-08-01-at-11-40-42-PM.png" alt="Arcee Spark" 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>Acknowledgements
We extend our deepest gratitude to PrimeIntellect for being our compute sponsor for this project.
- Created
- Aug 10, 2024
- Updated
- Aug 10, 2024