Fahadh

#17 opened 2 months ago by

New activity in LargeWorldModel/ultrachat_qa_mix_128K 4 months ago

What does it mean to pre-pack UltraChat data?

#1 opened 4 months ago by

New activity in gradientai/Llama-3-8B-Instruct-Gradient-1048k 4 months ago

Rope Theta Value Difference?

#24 opened 4 months ago by

New activity in CohereForAI/aya-23-8B 4 months ago

What Does `elif false == true` means in chat template?

#4 opened 4 months ago by

New activity in mistralai/Mistral-7B-Instruct-v0.2 5 months ago

What is the max. content length of Mistral-7B-Instruct-v0.2?

17

#43 opened 8 months ago by

hanshupe

New activity in databricks/dbrx-instruct 6 months ago

The fused expert parameters means load_in_4bit doesn't work properly, nor does LoRA

31

#10 opened 6 months ago by

tdrussell

New activity in LnL-AI/dbrx-base-converted-v2 6 months ago

Ready for Testing...

9

#1 opened 6 months ago by

Qubitium

Fix import typo

#2 opened 6 months ago by

New activity in databricks/dbrx-instruct 6 months ago

Failing to 4-bit quantize with BitsAndBytes

#16 opened 6 months ago by

simsim314

New activity in microsoft/phi-2 6 months ago

Target modules {'out_proj', 'Wqkv'} is not found in the phi-2 model how can I fix this error?

#115 opened 7 months ago by

roy1109

New activity in liuhaotian/llava-v1.6-mistral-7b 7 months ago

Some value in config is not used?

#7 opened 7 months ago by

New activity in sshh12/Mistral-7B-LoRA-AudioWhisper 7 months ago

Where is the adapter_model.bin?

#1 opened 7 months ago by

New activity in microsoft/phi-2 8 months ago

Model token size is bigger than tokenizer size?

#97 opened 8 months ago by

Why inside `modeling_phi.py`, the output from Self Attention is not becoming the input of MLP?

#94 opened 8 months ago by

New activity in openchat/openchat_sharegpt_v3 11 months ago

-100 vs 0 in label?

#2 opened 11 months ago by

New activity in Yukang/Llama-2-13b-chat-longlora-32k-sft 12 months ago

Why this model kept generating \n when loaded with text generation web ui?

4

#2 opened 12 months ago by

New activity in TheBloke/falcon-40b-instruct-GPTQ about 1 year ago

Offloading to cpu not working?

#21 opened about 1 year ago by

New activity in TheBloke/falcon-40b-sft-mix-1226-GGML about 1 year ago

Can it be loaded using text generation web ui?

#2 opened about 1 year ago by

New activity in syzymon/long_llama_3b about 1 year ago

clean_up_tokenization_spaces in tokenizer_config.json?

#3 opened about 1 year ago by

New activity in TheBloke/Llama-2-70B-GPTQ about 1 year ago

The `main` branch for TheBloke/Llama-2-70B-GPTQ appears borked

11

#3 opened about 1 year ago by

Aivean

New activity in TheBloke/Llama-2-7B-fp16 about 1 year ago

Llama-2-7B-Chat-fp16?

#1 opened about 1 year ago by

New activity in TheBloke/LongChat-13B-GPTQ about 1 year ago

Does max_position_embeddings really the parameter to be changed?

3

#1 opened about 1 year ago by

New activity in lmsys/longchat-13b-16k about 1 year ago

Please add the monkey patch so it can be load using transformers with `trust_remote_code=True`

#1 opened about 1 year ago by

New activity in TheBloke/Vicuna-13B-1-3-SuperHOT-8K-GPTQ about 1 year ago

How do you Quantize the model?

#3 opened about 1 year ago by