-
Issue:
SPHINX Tiny 1k seems to output gibberish responses for any image. Raising temperature allows for even more gibberish while lowering lessens gibberish.
Initially tried all the model checkpoi…
-
Hi~
I use c++ to execyte llama2 70B benchmark test. I meet the error "./cpp/build/benchmarks/gptSessionBenchmark: symbol lookup error: ./cpp/build/benchmarks/gptSessionBenchmark: undefined symbol: _…
-
how to train llama2-7b in a100 80G gpu?
-
I've been doing some experimentation with llama2 on both 7b and 70b, and at startup there is a significant hang time prior to the start of training.
On 7b it's ~3-5 minutes, and on 70b it's about 3…
-
obsidian-ollama options doesn't allow to be changed unless you change the code directly.
So, it means, it only allows llama2 for now. I'm so lazy, I will try this plugin when you fix the code.
-
### System Info
-CPU: x86
Memory: over 300G
GPU: 8 x V100
No IB, No nvlink, NCCL use socket for communication
Driver:
+-----------------------------------------------------------------------…
-
First of all I want to say a big thank you for developing the Llama.swift / CameLLM libraries.
I am working on a new project and trying to use https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML , b…
-
I am encountering a "forbidden error" when attempting to download Llama 3 from the official repository. This issue prevents me from accessing the model files necessary for my project.
I'll also r…
-
Hello, thank you for the work you are doing.
Does llama-adapter-v2 support llama2 or is it only working with llama?
I am able to pretrain with the weights of llama2 but the inference results do no…
-
I am curious whether you only used llama2 13b to create data when generating your generation model's training data, or if you also used llama2 7b to generate generation model's training data.