-
### Background
For large document understanding or tasks like code completion, it's often beneficial to have a large context length e.g. > 8K. In order for this to be enabled by default, a model wo…
-
Issue is to track evaluation of RAG implementations.
Frameworks:
- F
Papers:
- F
- F
One-Offs:
- https://github.com/microsoft/promptflow/tree/main/examples/flows/evaluation/eval-qna-rag…
-
Training command
```
(base) root@a3c636c20700:/workspace/gdrnpp_bop2022# CUDA_VISIBLE_DEVICES=0 python ./core/gdrn_modeling/main_gdrn.py --config-file configs/gdrn/tless/convnext_a6_AugCosyAAEG…
-
Hi guys,
I'm just load testing the API to see how fast we can read and write documents with OM library.
I've create a Model like:
```
[Document(IndexName = "aggregations-idx", StorageType =…
-
I am facing this issue while using `zigzag_ring_attn` with 128k context length. Has anyone run into the same problem?
```
[rank0]: File "/app/c2j-long-context-model-training/EasyContext/easy_con…
-
### ⚠️ Please check that this feature request hasn't been suggested before.
- [X] I searched previous [Ideas in Discussions](https://github.com/axolotl-ai-cloud/axolotl/discussions/categories/ideas) …
-
Hi,
I recently came across an issue when using context parallelism for splitting long sequence with NeMo and Transformer Engine. The context parallelism splits sequence length across GPUs and use p…
-
```
(textgen) [root@pve-m7330 sparsegpt]# python llama.py ../text-generation-webui/models/TinyLlama-1.1B-Chat-v1.0/ wikitext2 --nsamples 10
Token indices sequence length is longer than the specified…
-
**Is your feature request related to a problem? Please describe.**
MTK is a fairly large dependency that is really two packages in a trench coat.
Projects like DAECompiler and (I expect) JuliaSimC…
-
### System Info
- `transformers` version: 4.41.2
- Platform: Linux-5.4.0-173-generic-x86_64-with-glibc2.31
- Python version: 3.10.0
- Huggingface_hub version: 0.23.3
- Safetensors version: 0.4.3
…