A LLaVA model fine-tuned from Llama 3 Instruct with better scores in several benchmarks.
8B
8,208 Pulls Updated 12 days ago
Updated 12 days ago
12 days ago
44c161b1f465 · 5.5GB
model
archllama
·
parameters8.0B
·
quantizationQ8_K
4.9GB
template
{{ if .System }}<|start_header_id|>system<|end_header_id|>
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
{{ .Response }}<|eot_id|>
254B
projector
624MB
params
{"num_ctx":4096,"num_keep":4,"stop":["<|start_header_id|>","<|end_header_id|>","<|eot_id|>"]}
124B
Readme
llava-llama3
is a LLaVA model fine-tuned from Llama 3 Instruct and CLIP-ViT-Large-patch14-336 with ShareGPT4V-PT and InternVL-SFT by XTuner.