Srinivas Billa

New activity in meta-llama/Meta-Llama-3-8B about 2 months ago

Pytorch Bin version for gpt-fast

#96 opened about 2 months ago by

New activity in eastwind/llama-3-70b-instruct-hf-pt about 2 months ago

Can HF be convinced to release these .bin files properly?

#2 opened about 2 months ago by

artyom17

orignal -> original

#1 opened about 2 months ago by

artyom17

New activity in eastwind/llama-3-8b-instruct-hf-pt about 2 months ago

orignal -> original

#1 opened about 2 months ago by

artyom17

New activity in keyfan/grok-1-hf 3 months ago

4 Bit hf version here

#7 opened 3 months ago by

New activity in Narsil/mistral-medusa2 4 months ago

How to merge back into base model?

#1 opened 4 months ago by

New activity in h94/IP-Adapter-FaceID 5 months ago

Not working, what am i doing wrong?

#20 opened 6 months ago by

New activity in eastwind/tinymix-8x1b-chat 5 months ago

Just curious about what to expect from this model.

#3 opened 5 months ago by

stduhpf

New activity in eastwind/tinymix-8x1b-chat 6 months ago

just curious

#2 opened 6 months ago by

010O11

help

#1 opened 6 months ago by

Abhaykoul

New activity in TheBloke/dolphin-2.5-mixtral-8x7b-GGUF 7 months ago

Something wrong with q2

#1 opened 7 months ago by

New activity in huggingchat/chat-ui 7 months ago

💡 Future features

72

#176 opened about 1 year ago by

victor

New activity in Open-Orca/OpenOrca-Preview1-13B 11 months ago

Dataset Subsplits

#9 opened 11 months ago by

New activity in tiiuae/falcon-40b-instruct 12 months ago

[Bug] Does not run

17

#2 opened about 1 year ago by

catid

New activity in cognitivecomputations/dolphin 12 months ago

Task and Source Description

#2 opened 12 months ago by

New activity in Salesforce/xgen-7b-4k-base 12 months ago

GGML format

#2 opened 12 months ago by

slavag

New activity in WizardLMTeam/WizardLM_evol_instruct_70k 12 months ago

License?

#2 opened about 1 year ago by

brianjking

New activity in pankajmathur/dolly-v2_orca about 1 year ago

How were the answers generated?

#1 opened about 1 year ago by

New activity in TheBloke/open-llama-13b-open-instruct-GGML about 1 year ago

instructions?

#1 opened about 1 year ago by

0x1337

New activity in VMware/open-llama-13b-open-instruct about 1 year ago

Wow so quick!

#1 opened about 1 year ago by

New activity in facebook/MusicGen about 1 year ago

output license

10

#8 opened about 1 year ago by

Jaspior

New activity in OpenAssistant/falcon-40b-sft-top1-560 about 1 year ago

Issue with multi GPU inference.

10

#1 opened about 1 year ago by

New activity in openaccess-ai-collective/manticore-30b-chat-pyg-qlora about 1 year ago

What went wrong?

#1 opened about 1 year ago by

New activity in h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v2 about 1 year ago

params discrepancy in QLoRA?

#1 opened about 1 year ago by

New activity in togethercomputer/RedPajama-INCITE-7B-Base about 1 year ago

Can this be finetuned with QLoRA?

#4 opened about 1 year ago by

New activity in ybelkada/falcon-7b-sharded-bf16 about 1 year ago

missing file

3

#1 opened about 1 year ago by

New activity in h2oai/h2ogpt-gm-oasst1-multilang-2048-falcon-7b about 1 year ago

NoneType is not callable.

#1 opened about 1 year ago by

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

Slow and Gibberish when inferencing

11

#20 opened about 1 year ago by

New activity in tiiuae/falcon-7b-instruct about 1 year ago

not enough values to unpack (expected 4, got 3)

8

#19 opened about 1 year ago by

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

Caching doesn't work on multi gpu

#23 opened about 1 year ago by

New activity in tiiuae/falcon-40b about 1 year ago

Multi GPU inference issue

#39 opened about 1 year ago by

New activity in tiiuae/falcon-7b-instruct about 1 year ago

Sample code error - AttributeError: module 'torch.nn.functional' has no attribute 'scaled_dot_product_attention'