Products:
- Dataset: Function calling dataset (purchase here).
- v2 dataset (DEPRECATED). Purchase here.
- Pre-trained models:
- Yi 200k context 34B (purchase here) and 6B (purchase here) models.
- Llama 2 70B tuned for function calling. Purchase here.
- Mistral 7B tuned for function calling. Visit here.
- Deepseek Coder 1.3B, 6.7B and 33B fine-tuned for function calling. Visit here.
- CodeLlama 34B tuned for function calling. Purchase here.
- Llama 2 13B tuned for function calling. Purchase here.
- Script/Notebook to train for structured responses:
OR Buy access to the ADVANCED-fine-tuning repo, which includes the fine-tuning scripts for function calling.
Hello Ronan McGovern,
Hope you are doing well!
I have gone through your youtube video for fllama2 (function calling) and looks awesome. I would like to go through more about the fllama2 model. If you don’t mind can you provide free trail access for fllama2 – 13 model with limited requests so that we can test it and opt for purchasing the model.
Thanks,
Santhosh
Howdy Santhosh, thanks for the comment.
You can try out Llama 2 with function calling for free on the 7B model [here](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2). I’ve just pushed some improvements today. Check out also the performance video that is linked in the repo – it gives a sense for 7B versus 13B. Cheers, Ronan
Hello,
Could you do a function calling version of ‘Yi-34B-200k’? I’d like to pay for it.
Best,
Zack
Howdy! I’ve put in a request for a license as this model is only licensed for non-commercial use without permission.
btw, I’m getting very poor results on the model. I’ll see what the authors say, but seems a supervised fine-tuned is required at the very least.
Cool~ Looking forward to what you can get out of this model. Since this new pretrained model ranks top1 on Huggingface, I think it will be highly recommended. Considering its 34B size, if you can get this one with function calling works good, it could be a great sell.
Yi 6B and 34B are live now for function calling with 200k context length. See here: https://huggingface.co/Trelis/Yi-34B-200K-Llamafied-function-calling-v2
Great!
1. What’s the differences between Trelis/Yi-34B-200K-Llamafied-function-calling-adapters-v2 and Trelis/Yi-34B-200K-Llamafied-function-calling-v2?
2. If I want to learn how to finetune the function calling, Dataset and Script/Notebook to train for structured responses are what I need to buy, aren’t they?
3. You said “btw, I’m getting very poor results on the model. I’ll see what the authors say, but seems a supervised fine-tuned is required at the very least.” What happend? Is the result good neough now?
Thanks for your work!
1. You’ll get access to both. The adapter model allows you to load the base model and then apply the adapter. It can be useful if you wish to apply multiple adapters. It’s a specific advanced use case.
2. Yes, the Dataset and the notebook to train.
3. Yes, the prompt format wasn’t clear and that was affecting the model. I’ve put the correct prompt format now in the model card.
Hey I love your work,
could you consider creating a function-calling version of: https://huggingface.co/jphme/em_german_leo_mistral
We would love paying for that.
Cheers Simon
Howdy, I’ve just posted a question about the license: https://huggingface.co/jphme/em_german_leo_mistral/discussions/2 so I can understand whether it’s allowed to sell fine-tunes or not.
As a backup option, you could fine-tune yourself using the function-calling script and dataset. For a 7B model, you could do it in Colab with QLoRA on a T4 if you turn off flash attention.
But let’s see what the authors say first.
Okeydoke, the model is ready here Simon: https://huggingface.co/Trelis/em_german_leo_mistral-function-calling-v2
Clicking on dataset shows that the link is no longer active.
Thanks! Fixed now