-
### Summary
- Provide k-quant models
- Maintain existing gguf models
- Embedding models
- [x] [second-state/Nomic-embed-text-v1.5-Embedding-GGUF](https://huggingface.co/second-state/Nomic-…
-
Looks like Phi-3 Instruct is in @nomic_ai's gpt4all now: https://github.com/nomic-ai/gpt4all/commit/4193533154fc227bf6ce40ec1dff19aba1ee3929
I tried this:
```bash
llm -m Phi-3-mini-4k-instruct …
-
### System Info
- M1 Pro 16Gb
- I suppose PHI-3 demo uses version 2.17.1
### Environment/Platform
- [X] Website/web-app
- [ ] Browser extension
- [ ] Server-side (e.g., Node.js, Deno, Bun)
…
-
After running multiple times the command:
```
cargo run --release --features metal --example phi -- --model 3 --prompt "The best thing about coding in rust is "
```
I realized a very degrading…
-
The developed benchmark will be used to compare the Solidity performance of Qwen2 1.5b and Phi 3 Medium.
-
Good afternoon everyone!
We know that `Phi-3-mini-4k-instruct` has been suffering from some gibberish outputs when used with HuggingChat and I think I have been finally able to track where the issu…
-
**Background**
We evaluate the performance with llama-bench from ipex-llm[cpp] and [the benchmark script](https://github.com/intel-analytics/ipex-llm/tree/main/python/llm/dev/benchmark) , to compar…
-
Hi @Dan-wanna-M!
I wanted to integrate your great work here into mistral.rs and Candle. However, when testing with the `microsoft/Phi-3.5-mini-instruct` model's tokenizer using the below code, I ge…
-
**Describe the bug**
Got not useful error when trying to run phi-3.5-mini-instruct-onnx model locally on Windows.
```bash
RuntimeError: Error opening \cuda\cuda-int4-awq-block-128\phi-3.5-mini-instruc…
-
**Describe the bug**
The model will load but inference fails with a runtime error.
**To Reproduce**
Steps to reproduce the behavior:
1. Download any model in `https://huggingface.co/microsoft/…