nsheth/
llava-llama-3-8b-v1_1-int4:latest

2,093 1 year ago

vision

1 year ago

44c161b1f465 · 5.5GB ·

model
llama
·
8.03B
·
Q4_K_M
projector
clip
·
312M
·
F16
params
{ "num_ctx": 4096, "num_keep": 4, "stop": [ "<|start_header_id|>", "<|en
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Pr

Readme

Model

Source https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf

Modified for easy to use with ollama

llava-llama-3-8b-v1_1 is a LLaVA model fine-tuned from meta-llama/Meta-Llama-3-8B-Instruct and CLIP-ViT-Large-patch14-336 with ShareGPT4V-PT and InternVL-SFT by XTuner.

Note: This model is in GGUF format.

Resources: