Models

Llama-2-13b-hf-eli5-cleaned-1024_qlora_merged

Mellum-4b-base-mlx-fp16

Athenea-4B-Thinking

Qwen3-4B-Instruct-2507-mlx-fp16

Qwen2.5-Coder-3B-Instruct-Distill-Qwen3-Coder-Next-abliterated

ticket-triage-qwen3

wifuGPT-1.7B

RN_TR_R2

Qwen3-0.6B-Uncensored

borealis-1b-instruct-preview-mlx

medgemma-ECG-C-V2

ETLCH-instruct_based_on_llama3.2-1b_taiwan_traditional_chinese

Noir-Ultra

qwen25-coder-3b-python-expert-16bit

llama-2-13b

Llama-2-13B-german-assistant-v1

Llama2-7B-SFT-LIMA-fp16

Llama-2-13b-hf

Llama-2-7b-instruct

Redmond-Puffin-13B

ellie_llama_2_7b

llama-2-7b-guanaco-dolly-8bit-sharded

Llama_2_13b_NEE

llama2chat7b

llama2-7b-merged-finnish-alpaca-buggy

llama-2-13b-chat-hf

llama-2-13b-code-alpaca

Llama-2-7b-german-assistant-v2

llama-2-7b

llama-2-7b-resharded

llama-2-7b-legal-laws

llama-2-7b-instruct-maths-4bitshards

LLaMa-2-FrenchMedMCQA

alpaca_lora_ja_en_emb-7b

llama-2-7b-miniguanaco

Kimiko-13B-fp16

instruct-tuned-llama-7b-hf-alpaca_gpt_4_5_000_samples

llama-2-7b-miniguanaco

hermes-kimiko-7b

finallyworks

LLama2KimikoChat

LLaMaCoderAll