nvidia
/

Llama3-ChatQA-1.5-70B

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (4)

Why do various companies keep using hard-coded system prompt in the chat template?

#17 opened 5 months ago by

how do i erase this after downloading it locally??

#16 opened 5 months ago by

[AUTOMATED] Model Memory Requirements

#15 opened 7 months ago by

model-sizer-bot

The Model Stop Engaging in conversation

#14 opened 7 months ago by

generation_config.json adds a mapping with the special token '<|im_end|>' to solve the problem of non-stop generation when <|im_end|> is encountered.

#13 opened 7 months ago by

The tokenizer adds a special token '<|im_end|>' to solve the problem of non-stop generation when encountering <|im_end|>.

#12 opened 7 months ago by

About tokens used in this model.

#8 opened 8 months ago by

Multi-lang?

#6 opened 8 months ago by

Upload to ollama

#5 opened 8 months ago by

Adding `safetensors` variant of this model

#4 opened 8 months ago by

🚩 Report: Legal issue(s)

#3 opened 8 months ago by deleted

Should be "Llama 3ChatQA-1.5-70B"

#2 opened 8 months ago by

Concerns regarding Prompt Format

#1 opened 8 months ago by