-
**Is your feature request related to a problem? Please describe.**
I'm fine tuning gemma models. I'd like to be able to:
* add dropout to models loaded with `from_preset`
* remove dropout from …
-
@gjb2048 could you please take a look at this issue, it did work before but I think because of the 'hand' development we accedentily broke the feature?
I created a video for clarification: https:/…
-
I created a tar file out of a unsloth fine-tuned model(base-model: unsloth/gemma-2b-bnb-4bit) using PEFT and pushed it to gcsBucket. I am downloading the artifacts from gcs bucket, extracting the fil…
-
Right now the vector DB is working (#7) and we also made the ANN distance thresholds configurable (#35), but for proper RAG it'd be great to have re-ranking. Using Gemini this could mean many calls. M…
-
Hi there,
The current notebook for LLM on a conversational dataset has some technical inaccuracies. The instructional versions of Llama and Gemma are only trained on the assistant role, not on the …
-
I used [llm_inference](https://github.com/googlesamples/mediapipe/tree/main/examples/llm_inference) sample with `gemma-2b-it-cpu-int4.bin` on Pixel 8 Pro emulator.
The prefill speed seems to be in…
-
While generating any text with a specified value of max_length, the generated text keeps repeating several times until the output spans the value of max_length. An example of the above is using the fo…
-
### What is the issue?
hi? I'm studying fine tuning.
I learned using the "unsloth/gemma-2-2b-it" model.
I created the dataset myself and it contains less than 100 cases.
I want to use only the fin…
-
i cant get it to work with any of L3, or Gemma 2 models. they all throw errors. tried both llamacpp_HF and llamacpp.
-
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = "unsloth/gemma-2-9b-bnb-4bit",
max_seq_length = max_seq_length,
dtype = None,
load_in_4bit = True)
I noticed models ar…