imoneoi / openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

https://openchat.team

imoneoi/openchat Issues

License needs copyright template filled out
Updated 7 days ago
A question about the prefix of only SFT
Closed a month ago1
use instructor in openchat
Updated a month ago1
huggingface down: openchat can't be started
Updated a month ago1
About performance of LLama (llama2, llama3) model
Updated a month ago1
For 💻Online Demo It has been broken out.
Updated a month ago2
opchatdataset.estimate_num_batches returns 0 at the beginning of training, and training-stuck problem
Closed a month ago1
repeat the output content until the maximum output length is set
Updated a month ago2
Cannot create data file
Updated 2 months ago1
Does the current ochat.training_deepspeed.train only train v.3.2? How to train v.3.5?
Updated 2 months ago1
Single GPU vs multiple GPU (tensor parallel) suggestion for API Server
Updated 2 months ago3
Error running new model openchat-3.5-0106-gemma on RTX 4090 24GB machine, works with older mistral based model
Closed 2 months ago2
How was openchat/openchat-3.5-0106-gemma created?
Updated 2 months ago2
openchat.team is down for 3 days
Updated 2 months ago1
about data
Updated 2 months ago
weighted_token_accuracy
Updated 2 months ago
WARNING: Error in configuration: macro '\frac' failed its substitution!
Updated 2 months ago
Error when using openchat/openchat-3.5-0106-gemma in text-generation-inference
Updated 2 months ago
llama_model_load: error loading model: create_tensor: tensor 'output.weight' not found
Updated 2 months ago1
Exception in ASGI application
Updated 2 months ago3
Can not Reproduce benchmarks
Closed 2 months ago4
Was the chat template applied in ochat/config/conversation_template.py?
Updated 2 months ago
in llama.cpp load gguf has some issue in it
Updated 2 months ago
Shall we add a Contrib Guide .md (linked and separate from README)?
Updated 2 months ago
What is a minimum hardware requirements for setup as a sever ?
Updated 2 months ago
How to get around the template error in OpenChat 3.5 - 0106?
Updated 2 months ago1
Feature request: Allow run_eval to use more than 1 GPU
Updated 2 months ago
How was model imone/Mistral_7B_with_EOT_token created? Any details?
Updated 2 months ago1
Using anything > 2048 for batch_max_length during training results in cuda index errors
Updated 2 months ago1
Why the trained model does not produce the answer provided in the training data?
Updated 3 months ago
HjsonDecodeError("Bad key name (eof)", s, end) during training
Updated 3 months ago3
OpenChat API Non-Deterministic Behavior
Closed 3 months ago2
How many epochs did you use to train openchat 3.5?
Updated 3 months ago1
Question for https://huggingface.co/openchat/openchat-3.5-0106/blob/main/openchat.json
Updated 3 months ago1
Question about `--per-sequence-loss`
Updated 3 months ago1
`pip install ochat` - name 'nvcc_cuda_version' is not defined
Updated 3 months ago4
There is a 7B model, good at math: https://github.com/deepseek-ai/DeepSeek-Math.
Updated 3 months ago
What is the meaning of padding-free in ReadMe?
Updated 3 months ago
run multiple instances on a single gpu
Updated 4 months ago
I tried to pre-tokeinzation but failed
Updated 4 months ago
How to finetune openchat for downstream apps?
Updated 4 months ago
Extending your training section in ReadMe?
Updated 4 months ago
In the Web UI: https://openchat.team/, how can we specify "condition": "Math Correct"?
Updated 4 months ago
Could the idea of Self-Play Fine-Tuning be used in C-RLFT?
Updated 4 months ago
API token
Updated 4 months ago1
distill openchat
Updated 4 months ago
the website requires an openAI API key to work
Closed 4 months ago2
The AI on the site openchat.team is down
Closed 4 months ago1
the model of Pre-tokenized dataset openchat_v3.2_super.train.parquet is Llama2 or Mistral?
Updated 4 months ago1
did ```calculate_auto_lr``` affect a lot?
Closed 4 months ago4