-
Phi-3-mini-128k-instruct has the same number of parameters and same architecture as Phi-3-mini-4k-instruct, unless I am mistaken. Would it be possible for unsloth to support inference for this model a…
-
## Describe the bug
I got error
directory: `/Users/yuta/ghq/github.com/EricLBuehler/mistral.rs/mistralrs/examples`
mymachine environment ```
ProductName: macOS
ProductVersion: …
-
Currently session creation fails for onnx models with external data (i.e. any model larger than 2GB) in linux-x64.
For instance, trying to get input/output info for the following model: https://hug…
-
Let's allow developers to register a new LLM in a web browser as a web extension, which then would be able to be chosen in #8. The model would be in a TFLite [FlatBuffers](https://flatbuffers.dev/) fo…
-
Is there any API for linking an downloaded model to ollama from elsewhere. Suppose the model is downloaded before installing ollama, is there any way to link the model to ollama?
-
## ⚙️ Request New Models
- Link to an existing implementation (e.g. Hugging Face/Github): https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf
- Is this model architecture supported by ML…
-
There could be more than one LLM in a web browser (built-in or added as a web extension). Let's show users the list of available LLMs (using their IDs) and allow them to optionally choose a model when…
-
[MiniCPM3-4B](https://huggingface.co/openbmb/MiniCPM3-4B) is the 3rd generation of MiniCPM series. The overall performance of MiniCPM3-4B surpasses Phi-3.5-mini-Instruct and GPT-3.5-Turbo-0125, being …
-
### Bug Description
I'm doing RAG using llama-index.The model is Phi3-mini-4k. I have experimented all the models that supports sub-queryengine. When comparing those models, I got pretty good results…
-
os: windows
I think my environment is ready
use jupyter notebook locally
when i run these:
"from unsloth import FastLanguageModel
import torch
max_seq_length = 8192 # Choose any! We auto sup…