dromeuf

Hi Priestru, I am working with last Ubuntu 22.04 LTS with Anaconda 2.4 env python 3.10.9 I was getting several errors and warnings resolved by installing the cudatoolkit package 11.3.1...

I added the 2 lines but I still have the error. (textgen) dr@pcdr:~/text-generation-webui$ **git pull** remote: Enumerating objects: 24, done. remote: Counting objects: 100% (24/24), done. remote: Compressing objects: 100%...

My run use unsloth 2024.8. Building wheels for collected packages: unsloth Building wheel for unsloth (pyproject.toml) ... done Created wheel for unsloth: filename=unsloth-2024.8-py3-none-any.whl size=136912 sha256=7c408cab17d207a06e6b22693fac30b498acecb062c06f2b023b28ee42014a27 Stored in directory: /tmp/pip-ephem-wheel-cache-u3imsks4/wheels/ed/d4/e9/76fb290ee3df0a5fc21ce5c2c788e29e9607a2353d8342fd0d Successfully...

Hi Dan, I am not using apply chat template. I am using my direct conversational dataset. Example in my post (example corpus qa io lines...). I try différent test and...

> Wait when you mean direct conversational dataset - did you use our conversational style notebooks (ShareGPT / Llama -3?) Hi Dan, @danielhanchen I've already used your example of **unsloth.chat_templates...

> @dromeuf Actually wait did you use `tokenizer.apply_chat_template`? or our conversational notebooks - apologies but just after you posted, I updated all Llama 3.1 tokenizers - so probably why it's...

> @dromeuf Oh could you try `chat_template = "llama-31",` which is for Llama 3.1 - I just added it in last week. > I did wonder about that, but I...

> @dromeuf Oh could you try `chat_template = "llama-31",` which is for Llama 3.1 - I just added it in last week. > Hi Dan @danielhanchen , I changed the...

> @dromeuf The date is correct - I asked the HF team to enquire about this, but Llama 3.1 Instruct's system prompt has the date. > So there ! ;-)...

> @dromeuf Oh saw your email - will definitely take a look Hi Dan @danielhanchen , were you able to work with my dataset and notebook to solve or identify...