GGUF models by ProjectZLLM
36 GGUF models quantized by ProjectZLLM on Hugging Face. Sizes run from 3.82B to 8.03B parameters. The longest trained context is 128K tokens.
LL
SFT Llama 3 8B Instruct email470 4epoch
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
orpo-passive-Llama-3-8B-Instruct-user-NoI_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
orpo-passive-Llama-3-8B-Instruct-prompt-1_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
orpo-passive-Llama-3-8B-Instruct-user-NoI-10_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
orpo-passive-Llama-3-8B-Instruct-prompt-1-3epoch-cos_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB
LL
orpo-passive-Llama-3-8B-Instruct-prompt-addActive_gguf
Llama · ProjectZLLM
Params8.03B
Context8K
Q4_K_M4.9 GB