-
It would be really powerful to be able to integrate [LM Formate Enforcer](https://github.com/noamgat/lm-format-enforcer) with Ollama. It already supports llama.cpp as well.
-
Tried following the wiki
https://github.com/likelovewant/ROCmLibs-for-gfx1103-AMD780M-APU/wiki/Unlock-LM-Studio-on-Any-AMD-GPU-with-ROCm-Guide#using-amd-graphics-cards-with-lm-studio
Copied the fi…
-
When executing `cosyvoice.llm.llm.TransformerLM.inference()`, the variable `offset` in the function is not used,see [code line ](https://github.com/FunAudioLLM/CosyVoice/blob/8555ab4ded5ccfa7d2fe3a999…
-
On lines 76 and 77 of the preprocessing.py file, I want to know what is the purpose of these two lines?
![image](https://github.com/TadasBaltrusaitis/OpenFace/assets/110211332/02795895-c5d3-438f-96cd…
-
![image](https://github.com/user-attachments/assets/8cb080d3-d38b-4514-a71d-0e6a981bea1e)
Hello! Thank you for publicly disclosing such excellent work. When I entered 'Introduction yourself' in the f…
-
### Feature Request
https://lmstudio.ai/
Could LM Studio support be added. LM Studio is much more versatile than ollama and allows you to download and run GGUF models directly from Hugging Face
#…
EDLLT updated
12 hours ago
-
I'm attempting to train LLaMA-3 using Megatron-LM but have encountered an issue: LLaMA-3 utilizes Tiktoken for tokenization and doesn't provide a tokenizer.model file, which is required by Megatron-LM…
SDsly updated
1 month ago
-
I am trying to eval the finetuned model 70B with torch run and getting error
Here is my config file
```
model:
_component_: torchtune.models.llama3.lora_llama3_70b
lora_attn_modules: ['q_pr…
-
Replicating my issue from Discord here.
I'm following the provided notebook on my dataset, but it keeps throwing the following error:
Unsloth: Untrained tokens of [[128042, 128036]] found, but e…
-
When you trained chronos from t5 initialized with random or language weights, did you finetune `'encoder.embed_tokens.weight', 'decoder.embed_tokens.weight', 'lm_head.weight'` or while checkpointing, …