Mikael

New activity in bartowski/gemma-2-27b-it-GGUF 3 months ago

Prompt format <bos> not needed?

16

#3 opened 3 months ago by

eamag

New activity in microsoft/Florence-2-large 3 months ago

Fix Tasks examples

#4 opened 3 months ago by

New activity in cognitivecomputations/dolphin-2.9-llama3-8b 5 months ago

Poor quality output compared to Meta's Instruction Tune

#7 opened 5 months ago by

ElliottDyson

Fix Incorrect Prompt Template defined in tokenizer_config.json

#3 opened 5 months ago by

New activity in google/gemma-7b 7 months ago

Why the original GGUF is quite large ?

14

#11 opened 7 months ago by

nopainkiller

New activity in open-llm-leaderboard/open_llm_leaderboard 9 months ago

Announcement: Flagging merged models with incorrect metadata

82

#510 opened 9 months ago by

clefourrier

New activity in TheBloke/MixtralRPChat-ZLoss-GGUF 9 months ago

Minor Prompt Template Fix

#1 opened 9 months ago by

New activity in TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF 10 months ago

Q6_K appears to be broken (And maybe other K-Quants as well)

#11 opened 10 months ago by

New activity in Mikael110/llama-2-70b-guanaco-qlora about 1 year ago

where is the code to actually fine tune with qlora?

#4 opened about 1 year ago by

brando

What dataset was this model finetuned on?

#3 opened about 1 year ago by

saattrupdan

New activity in Mikael110/llama-2-7b-guanaco-fp16 about 1 year ago

Just couple of confusion to clear

4

#3 opened about 1 year ago by

Talha

New activity in TheBloke/StableBeluga2-70B-GPTQ about 1 year ago

Problems on runpod.io

11

#3 opened about 1 year ago by

olafgeibig

New activity in Mikael110/llama-2-70b-guanaco-qlora about 1 year ago

Woot!!! thank you <3

#1 opened about 1 year ago by

AARon99

New activity in TheBloke/llama-2-70b-Guanaco-QLoRA-GPTQ about 1 year ago

Fix creator name

#3 opened about 1 year ago by

New activity in Mikael110/llama-2-13b-guanaco-fp16 about 1 year ago

Train this model on coding datasets to make a BEAST coding model

4

#1 opened about 1 year ago by

rombodawg

New activity in TheBloke/llama-2-7B-Guanaco-QLoRA-GGML about 1 year ago

Fix name typo

#1 opened about 1 year ago by

New activity in Mikael110/llama-2-7b-guanaco-fp16 about 1 year ago

Why not the new prompt format?

#1 opened about 1 year ago by

SinanAkkoyun

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

Chat prompt format?

12

#3 opened about 1 year ago by

mike-ravkine

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

Remove invalid KoboldCpp option from examples

#2 opened about 1 year ago by

New activity in TheBloke/guanaco-65B-GGML over 1 year ago

Correct Prompt Template

#3 opened over 1 year ago by

New activity in OpenAssistant/falcon-40b-sft-mix-1226 over 1 year ago

Expand Output after deploying it on SageMaker

#3 opened over 1 year ago by

gdcoder

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

how much Vram does it take to run Falcon 40b

7

#44 opened over 1 year ago by

Toaster496

New activity in TheBloke/WizardLM-Uncensored-SuperCOT-StoryTelling-30B-GPTQ over 1 year ago

(Minor Issue) Fix broken GPTQ and GGML Links

#1 opened over 1 year ago by

New activity in TheBloke/guanaco-13B-GGML over 1 year ago

Same generation each time

#2 opened over 1 year ago by

jgranie

Prompt Format.