Deepseek Coder vs CodeLlama vs Claude vs OpenAI
Vložit
- čas přidán 12. 06. 2024
- Trelis.com - for inference, fine-tuning and function-calling scripts.
* Deepseek Inference *
One-click template: runpod.io/gsc?template=51tpe9...
TheBloke AWQ: huggingface.co/TheBloke/deeps...
* Deepseek 1.3B, 6.7B and 33B function-calling models *
huggingface.co/Trelis/deepsee...
* Inference Guide *
trelis.com/enterprise-server-...
* Fine-tuning Scripts *
trelis.com/advanced-fine-tuni...
Full Repo Includes:
- LLM Comparison Notebook from this video
- Supervised fine-tuning
- Unsupervised fine-tuning
- Quantization scripts
- Function calling / Structured response fine-tuning
- Embeddings notebook
OR buy only the LLM Comparison Notebook here: buy.stripe.com/5kAcNy8G12Hxg7...
Chapters:
0:00 Deepseek coder
0:24 Agenda
1:03 Model sizes and license
2:02 Prompt format
3:36 Inference on Runpod
5:05 Performance vs CodeLlama, OpenAI, Claude
7:04 Returning a sequence in reverse
10:40 Passkey retrieval
16:23 Website generation
24:20 Function calling
25:22 Resources - Věda a technologie
Awesome! Thanks for the template
I enjoyed the video, thanks for sharing. I am curious, do you think the NF4 quantization tripped up some of your results. How are the results different when using AWQ? What running the full model using bfloat16
NF4 probably has some effect, although I used it for both models so perhaps the relative effect is similar and the comparison is ok.
AWQ typically performance a bit worse than NF4, but better than GPTQ. I think I discuss that a little in the awq video.
Running bfloat16 is def best, you can check out this paper for relative performance: arxiv.org/pdf/2305.14314.pdf
interesting insights - thk you" - atm it seems that those big models are still very weak at certain tasks that seem to be rather simple. I tried getting out some info from table like info in the prompt from gpt-4 and it failed mostly even if the prompt is not long. this diappointed me hard as I really like the performance of gtp4 in many other tasks
Can you help me solve the two level programming model with constraints
Hi @Trelis Research, thank you for the great video, will you consider to make a video to discuss how to fine tune copilot style coding llms? Thanks
Could you give more of an example of a specific fine tune that would be helpful
9:54 here, gpt-3.5 actually failed, it skipped the "n"
oops, you're right. My brain is clearly a bad tool for grading