-
### System Info
- `transformers` version: 4.44.2
- Platform: Linux-3.10.0-1160.el7.x86_64-x86_64-with-glibc2.17
- Python version: 3.10.14
- Huggingface_hub version: 0.24.3
- Safetensors version: …
-
### What happened?
The llama.cpp tokenizer for Phi-3 has odd behavior, where re-tokenizing the same text over and over keeps adding whitespaces to the first non-BOS token. This has several issues:
…
-
### Describe the issue as clearly as possible:
`mlx-community/Phi-3-mini-4k-instruct-4bit` and `mlx-community/Phi-3-mini-4k-instruct-8bit` generate text without spaces when using `outlines`. Interes…
-
### Describe the bug
The `huggingface-cli` fails to download the `microsoft/phi-3-mini-4k-instruct-onnx` model because the `.incomplete` file of the `.onnx` data file is missing.
I assume the fi…
-
Ref: https://github.com/ggerganov/llama.cpp/pull/8687#issuecomment-2252155218
(cc @ggerganov)
TODO:
- Train some adapters based on stories15M and [stories15M_MOE](https://huggingface.co/ngxson/…
-
**Is your feature request related to a problem? Please describe.**
My company unfortunately cannot benefit from the AI power-tools because anything that involves code remote upload will be violatin…
-
### What happened?
The new Copilot+PCs with Qualcomm Snapdragon X processors (in my case a Surface 11 Pro with Snapdragon X Plus and 16GB RAM) are fast, and run llama.cpp on the CPU w/o issues. The…
-
**Describe the bug**
Is there an equivalent C API or method to the python "logits = generator.get_output("logits")" API that allows us to get the logit values of the output?
The documentation only…
WA225 updated
2 months ago
-
Hello,
many thanks for this very nice piece of work!
I couldn't get the finetune/finetune_lora scripts to run on a freshly launched ubuntu ec2 instance without a substantial refactoring of the …
-
Hi!
I do the fine tuning by full training, and get config.json, model.safetensors, special_tokens_map.json tokenizer.jsson, training_args.bin, generation_config.json, preprocessor_config.json, toke…