-
Hi! I want to know if llama3 has utilized Tensor Core in its code, and by default, it supports tensor core processing out of the box.
-
### Describe the feature
Is there any “**official results**” come out by OpenCompass?
I'd like to compare and double check.
I need results for Qwen2, Qwen2.5, GLM4, Llama3, Llama3.1
THANK YO…
-
## Problem Statement
To support Vision models on Cortex, we need the following:
- [ ] 1. Download model .gguf and mmproj file
- [ ] 2. `v1/models/start` takes in `model_path` (.gguf) and `mmproj` p…
-
When I run:
> RAYON_NUM_THREADS=6 CUDA_VISIBLE_DEVICES=0 python3 -m rest.inference.cli --datastore-path datastore/datastore_chat_small.idx --base-model meta-llama/Meta-Llama-3-8B-Instruct
I get:
…
-
Hello! We'd like to request the addition of our model, **Aloe**, to the MedConceptsQA leaderboard. Here are the HuggingFace model names:
- `HPAI-BSC/Llama3.1-Aloe-Beta-8B`
- `HPAI-BSC/Llama3.1-Alo…
-
Running the following command with Llama-3.1-8B-Instruct fails with a `AttributeError: 'function' object has no attribute 'pad_token'` error. I am using the adding_all_changess branch to replicate the…
-
### 🚀 The feature, motivation and pitch
ollama vision is new:
https://ollama.com/x/llama3.2-vision
providers:
inference:
- provider_id: remote::ollama
provider_type: remote::ollama
…
-
### What happened?
I'm trying to add an ollama via the ui. I choose Add Model, provider ollama, public model name "llama3.2", litellm model name "llama3.2", provide base URL (same as env below), then…
-
您好，我想用 lora 微调 internvl2-llama3-76b，8张A100 的负载非常不均衡，训练过程中后3张卡的显存利用率近似为0。
command:
swift sft \
--model_type internvl2-llama3-76b \
--model_id_or_path /lnt/workspace/lmm_share/model_hub/Open…
-
# Tokenizer Import Error When Using Ollama Models
## Description
When attempting to use Ollama models (llama3, llama3.1, mistral), the application fails due to a tokenizer import error. The error …