-
### Question
I want to use llama2 model, a bigger one, i use the model from huggingface. If i just change the model path, for example, just change the "--model_name_or_path" in pretrain.sh, can it al…
-
Has anyone tried running the Llama2 (https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML)model? After I load the model, the APP immediately crashes after sending out the prompt.
-
Like https://github.com/pytorch/executorch/issues/3264, another testing issue for https://github.com/pytorch/test-infra/pull/5122. I'll close this once done.
-
I have run through the entire process of llama2 and want to stress test and see the benchmark indicators.
Regarding ```max_tokens_in_paged_kv_cache```, I may not understand it well
Is it similar…
-
### 🚀 The feature, motivation and pitch
Recently the Maximal Update Parametrization ([muP, arxiv 2203.03466](https://arxiv.org/abs/2203.03466)) is becoming prevalent in large model training becaus …
-
Hi, thanks for your cool work!
I've trained the llama2 minigpt4-video model on ~500 short videos using stage 3 finetuning scripts, and the training loss converged to almost 0 (< 1e-4).
The train…
-
I am looking to test ChartAssistant on a certain type of graph my research group is interested in, but I am having trouble installing your model. Some questions:
- Do you need GPUs to use your mode…
-
**Feature / App description**
A clear and concise description of what the feature or app is about.
Add support for the above mentioned models / providers.
If adding new LLMs aligns with your goa…
-
I am trying to finetune large tables having 99 columns and 180 rows for complex sql queries. I am unable to finetune it as it has 6000 tokens. Can we do that using LLAMA2?. Please assist.
-
It works well when I use LLama2-7b-Chat, but when I changed the model to a new version mixtral-8x7b-v0.1Q2_K, when I ask the same question it seems that the robot gave a wrong answer, and it even chan…