An uncensored version of the original Llama-3.2-1B-Instruct, created via abliteration
2,800 Pulls 1 Tag Updated 1 year ago
Light version - GigaChat-3.1-Lightning: it shows the level of GPT-4o in arenas, but at the same time remains compact and fast (quantized Q4_K_M)
581 Pulls 1 Tag Updated 3 months ago
Pruned/masked heads version of gemma4-31b
205 Pulls 26 Tags Updated 2 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,
5 Pulls 1 Tag Updated 1 month ago
Plutus is a fine-tuned version of the LLaMA-3.1-8B model, specifically optimized for tasks in finance, economics, trading, psychology, and social engineering.
29.2K Pulls 1 Tag Updated 1 year ago
This is an uncensored version of Llama 3.1 8B Instruct with an uncensored prompt.
7,982 Pulls 45 Tags Updated 1 year ago
Fine-tuned version of Llama 3.1 1B, optimized for NER tasks on NBA sentences containing player and team names.
19 Pulls 1 Tag Updated 7 months ago
This model Microsoft updated Phi-3 Mini version (June 2024) (Phi-3.1 Mini)
3,985 Pulls 2 Tags Updated 2 years ago
The Amazon Prime Movie Expert is a specialised version of the Llama 3.1 8B model, fine-tuned to act as a high-precision database assistant for Amazon Prime Video content.
2 Pulls 1 Tag Updated 4 months ago
This version of bellman is finetuned from llama-3.1-instruct-8b. It's finetuned for prompt question answering, based on a dataset created from Swedish wikipedia, with a lot of Sweden-centric questions.
322 Pulls 3 Tags Updated 1 year ago
A Sinhala-adapted version of Google’s Gemma 3 4B, continually pre-trained on 10.7M Sinhala sentences with a custom 16k vocabulary using 4-bit LoRA.
205 Pulls 1 Tag Updated 10 months ago
This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct that has been optimized for Indonesian language understanding and generation. The fine-tuning process utilized Low-Rank Adaptation (LoRA) to efficiently adapt the model while minimizi
150 Pulls 1 Tag Updated 11 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
4 Pulls 1 Tag Updated 2 months ago
Bfloat16 version of the Gemma 3 12B and 27b model
304 Pulls 4 Tags Updated 1 year ago
fine-tuned version of Qwen/Qwen2.5-32B-Instruct on the OpenThoughts-114k dataset, available in [F16, q8_0, q6_K, q4_K_S]
300 Pulls 4 Tags Updated 1 year ago
The model used is a quantized version of `Llama-3-Taiwan-8B-Instruct-128k`. More details can be found on the https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct-128k
355 Pulls 11 Tags Updated 2 years ago
A laser version of openchat/openchat-3.5-0106
127 Pulls 10 Tags Updated 2 years ago
A fine-tuned version of Gemma 3-1B that translates sentences between English and Morse code
39 Pulls 1 Tag Updated 1 year ago
llma version 3.2 with 1b parameter
25 Pulls 1 Tag Updated 1 year ago
Bfloat16 version of the Falcon 3 10B model.
8 Pulls 1 Tag Updated 1 year ago