bluuwhale/L3-SthenoMaidBlackroot-8B-V1
Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:Jun 9, 2024Architecture:Transformer0.0K Warm

bluuwhale/L3-SthenoMaidBlackroot-8B-V1 is an 8 billion parameter language model created by bluuwhale, merged using the Model Stock method with Sao10K/L3-8B-Stheno-v3.2 as its base. This model combines the strengths of Llama-3-Lumimaid-8B-v0.1-OAS and Jamet-8B-L3-MK.V-Blackroot, offering a merged architecture for general language tasks. It supports a context length of 8192 tokens, making it suitable for applications requiring moderate context understanding.

Loading preview...

Overview

bluuwhale/L3-SthenoMaidBlackroot-8B-V1 is an 8 billion parameter language model, a product of a merge operation using the mergekit tool. It leverages the advanced "Model Stock" merging method, as detailed in the paper "Model Stock", to combine the capabilities of several pre-trained models.

Merge Details

The model's foundation is Sao10K/L3-8B-Stheno-v3.2, which served as the base model during the merging process. It integrates components from two additional models:

  • Hastagaras/Jamet-8B-L3-MK.V-Blackroot
  • NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS

This strategic merge aims to consolidate the strengths of these individual models into a single, cohesive 8B parameter model, designed for general-purpose language understanding and generation tasks. The model operates with a context length of 8192 tokens.

Potential Use Cases

  • General text generation and completion
  • Conversational AI and chatbots
  • Content creation requiring moderate context
Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p