Hugging Face's logo

brandonbeiler
/
InternVL3_5-38B-FP8-Dynamic

Image-Text-to-Text
Safetensors
multilingual
vllm
internvl_chat
fp8
fp8-dynamic
llm-compressor
internvl3.5
internvl
conversational
custom_code
compressed-tensors
Model card Files
xet
Community
brandonbeiler commited on
Commit
bc94e29
·
verified ·
1 Parent(s): efcfd92

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -30,7 +30,7 @@ You can serve the model using vLLM's OpenAI-compatible API server.
30
  vllm serve brandonbeiler/InternVL3_5-38B-FP8-Dynamic \
31
  --quantization compressed-tensors \
32
  --served-model-name internvl3_5-38b \
33
- --reasoning-parser: qwen3 \
34
  --trust-remote-code \
35
  --max-model-len 32768 \
36
  --tensor-parallel-size 1 # Adjust based on your GPU setup
 
30
  vllm serve brandonbeiler/InternVL3_5-38B-FP8-Dynamic \
31
  --quantization compressed-tensors \
32
  --served-model-name internvl3_5-38b \
33
+ --reasoning-parser qwen3 \
34
  --trust-remote-code \
35
  --max-model-len 32768 \
36
  --tensor-parallel-size 1 # Adjust based on your GPU setup