Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
4.1M Pulls 5 Tags Updated 1 year ago
An uncensored, abliterated build of Meta's **Llama 3.1 8B Instruct**. Abliteration surgically removes the model's learned refusal direction while preserving its general capabilities
1,613 Pulls 2 Tags Updated 2 months ago
aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
897 Pulls 2 Tags Updated 6 months ago
The **Llama-3.1-8B-Instruct-STO-Master** is a high-performance fine-tune of Meta's Llama-3.1-8B-Instruct. This model represents the "Master Version" (Model E) of an extensive research project aimed at pushing the boundaries of 8B parameter architectures.
185 Pulls 1 Tag Updated 7 months ago
This model is a beginner-focused fine-tuning project that adapts Meta's Llama-3.1 8B Instruct base into a specialized technical expert for the Vellium search engine. Trained via Unsloth and 4-bit QLoRA on structural architectural data,
8 Pulls 1 Tag Updated 2 months ago
Modelo de IA especializado na Doutrina Espírita de Allan Kardec. Treinado sobre Llama 3.1 8B Instruct com QLoRA, cobrindo a obra integral de Kardec em domínio público: as 5 obras da Codificação + obras complementares + 12 volumes da Revista Espírita
6 Pulls 1 Tag Updated 4 months ago
Llama-3.1-Storm-8B outperforms both Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B! 🤗 Blog: https://huggingface.co/blog/akjindal53244/llama31-storm8b
38.1K Pulls 3 Tags Updated 2 years ago
This is an uncensored version of Llama 3.1 8B Instruct with an uncensored prompt.
8,947 Pulls 45 Tags Updated 2 years ago
8,579 Pulls 2 Tags Updated 2 years ago
NousResearch/Meta-Llama-3.1-8B-Instruct Korean finetuned model with SFT->RLHF->DPO
2,848 Pulls 2 Tags Updated 2 years ago
watt-tool-8B is a fine-tuned language model based on LLaMa-3.1-8B-Instruct, optimized for tool usage and multi-turn dialogue. It achieves state-of-the-art performance on the Berkeley Function-Calling Leaderboard (BFCL).
2,186 Pulls 1 Tag Updated 1 year ago
2,518 Pulls 2 Tags Updated 2 years ago
Llama 3.1 8B Instruct trained on 9,000,000 Claude Opus/Sonnet tokens
1,749 Pulls 1 Tag Updated 2 years ago
Outperforms Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B
1,357 Pulls 6 Tags Updated 2 years ago
LoRA-merged abliterated L3.1-8B GGUF from https://huggingface.co/grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF/tree/main
1,002 Pulls 1 Tag Updated 2 years ago
Llama-3.1-8b-Instruct
690 Pulls 1 Tag Updated 2 years ago
https://github.com/ollama/ollama/issues/6048
677 Pulls 2 Tags Updated 2 years ago
Llama-3.1-Storm-8B outperforms both Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B!
624 Pulls 13 Tags Updated 2 years ago
From HF：meta-llama/Llama-3.1-8B-Instruct
452 Pulls 1 Tag Updated 1 year ago
Model finetuned starting with llama 3.1 8b using a full precision LoRA he20, rank 64, alpha 16
460 Pulls 1 Tag Updated 1 year ago