-
```Traceback (most recent call last): File "e:\llm\TinyLlama\pretrain\tinyllama.py", line 17, in from lit_gpt.model import GPT, Block, Config, CausalSelfAttention File "E:\llm\TinyLlama\lit_g…
-
Could I kindly inquire as to why, given the relatively small size of the tinyllama model, the Strategy was made to utilize FSDP (Fully Sharded Data Parallel) instead of DDP (Distributed Data Parallel)…
-
In my opinion, the generation should be the same when draft model and target model is the same and temparature is 0.
But in this case, the output logits of draft model and target model have a bit d…
-
Something interesting occurred while upgrading to version 1.8.0. Previously, it had been throwing an "Out of Memory" error, but that issue has now been resolved. However, a new problem has surfaced, w…
-
-
I want to run the tinyllama model and I wonder if there a way to run GGUF models with this crate. It seem much more common that models are using the GGUF format over the GGML format for models and con…
-
Here is my training script
```
deepspeed tinyllava/train/train.py \
--deepspeed ./scripts/zero2.json \
--model_name_or_path checkpoints/TinyLlama-1.1B-Chat-v1.0/ \
--version plain…
-
### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a sim…
-
https://huggingface.co/apple/OpenELM
Has models ranging from 270M to 3B parameters. Would love to see more support for small models, since I'm stuck with 4gb VRAM currently. Tinyllama can't fill ev…
-
Hello,
First I'll say, really impressed by this library and looking forward to TTS!
I ran the example project on my android pixel 7 (Same one you used) and I am not seeing the same performance t…