None

#13 opened 2 months ago by

kk3dmax

New activity in mistralai/Mixtral-8x22B-Instruct-v0.1 2 months ago

First Word Ignored Issue / Single Word Instruction

20

#11 opened 2 months ago by

pandora-s

Prompt format

#12 opened 2 months ago by

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 2 months ago

Incomplete Answers

7

#59 opened 6 months ago by

samparksoftwares

New activity in turboderp/Mixtral-8x22B-Instruct-v0.1-exl2 2 months ago

Weird answers for short instructions such as "Hi"?

#2 opened 2 months ago by

New activity in mistral-community/Mixtral-8x22B-v0.1 3 months ago

Instruct version?

4

#13 opened 3 months ago by

New activity in cognitivecomputations/dolphin-2.5-mixtral-8x7b 6 months ago

Higher PPL than Mixtral?

#11 opened 7 months ago by

New activity in LoneStriker/dolphin-2.2-70b-6.0bpw-h6-exl2 7 months ago

exl2-2 please?

8

#1 opened 7 months ago by

New activity in cognitivecomputations/dolphin-2.2-70b 7 months ago

Safetensors version?

#2 opened 8 months ago by

matatonic

New activity in cognitivecomputations/dolphin-2_2-yi-34b 7 months ago

Casual system prompts give very bad results

#7 opened 7 months ago by

New activity in LoneStriker/dolphin-2.2-yi-34b-4.0bpw-h6-exl2 7 months ago

tokenization_yi.py

#1 opened 7 months ago by

Stilgar

New activity in cognitivecomputations/dolphin-2_2-yi-34b 7 months ago

No need to trust_remote_code

#6 opened 7 months ago by

Weyaxi

New activity in cognitivecomputations/dolphin-2.2-70b 7 months ago

Orca 2 upgrade planned?

#6 opened 7 months ago by

New activity in Panchovix/goliath-120b-exl2 8 months ago

3bpw not working anymore

#1 opened 8 months ago by

mpasila

New activity in cognitivecomputations/dolphin-2.2-70b 8 months ago

Keep up the good work!

#3 opened 8 months ago by

exl2 quanitzed version

#1 opened 8 months ago by

New activity in jondurbin/airoboros-l2-c70b-3.1.2 8 months ago

Any positive results so far?

#1 opened 8 months ago by

New activity in WizardLMTeam/WizardLM-70B-V1.0 8 months ago

Any plans for V1.1?

#17 opened 8 months ago by

New activity in LoneStriker/zephyr-7b-beta-8.0bpw-h6-exl2 8 months ago

h8 instead of h6 for 8bpw versions

#1 opened 8 months ago by

New activity in cognitivecomputations/dolphin-2.2.1-mistral-7b 8 months ago

Really impressive!

15

#1 opened 8 months ago by

New activity in Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors 10 months ago

Update bin2safetensors/convert.py

#2 opened 10 months ago by

New activity in simsim314/WizardLM-70B-V1.0-HF 10 months ago

Script used to convert the original model

#1 opened 10 months ago by

New activity in Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors 10 months ago

Update bin2safetensors/convert.py

#1 opened 10 months ago by

New activity in Panchovix/airoboros-l2-70b-gpt4-1.4.1_5.0bpw-h6-exl2 10 months ago

Convertion process

#1 opened 10 months ago by

New activity in uni-tianyan/Uni-TianYan 10 months ago

Prompt format?

#3 opened 10 months ago by

New activity in fangloveskari/ORCA_LLaMA_70B_QLoRA 10 months ago

Prompt format?

#9 opened 10 months ago by

New activity in migtissera/Synthia-70B-v1.2 10 months ago

I wonder what is the difference between version 1.1 and 1.2

16

#2 opened 10 months ago by

Flanua

New activity in TheBloke/StableBeluga2-70B-GPTQ 11 months ago

GGML version possible/coming?

2

#8 opened 11 months ago by

New activity in cognitivecomputations/WizardLM-33B-V1.0-Uncensored about 1 year ago

Very good model, suprisingly better than WizardLM-30B, why?

#2 opened about 1 year ago by

New activity in Panchovix/WizardLM-33B-V1.0-Uncensored-SuperHOT-8k-4bit-32g about 1 year ago

Best parameters for 24GB VRAM?

#2 opened about 1 year ago by

Prompt format?

#1 opened about 1 year ago by

New activity in Panchovix/WizardLM-33B-V1.0-Uncensored-SuperHOT-8k about 1 year ago

Prompt format?

#1 opened about 1 year ago by

New activity in lmsys/vicuna-33b-v1.3 about 1 year ago

Prompt format?

5

#1 opened about 1 year ago by

New activity in MetaIX/GPT4-X-Alpasta-30b about 1 year ago

Excellent model - Any plans for further finetuning and/or 65b?

#6 opened about 1 year ago by

New activity in open-llm-leaderboard/open_llm_leaderboard about 1 year ago

[Feature Request] Add timestamp (date - time) to evaluation tables

#43 opened about 1 year ago by

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

Unfortunately I can't run on text-generation-webui

11

#1 opened about 1 year ago by

Suoriks

New activity in TheBloke/guanaco-65B-GPTQ about 1 year ago

You're blazing fast!

9

#1 opened about 1 year ago by

New activity in TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ about 1 year ago

Gibberish on 'latest', with recent qwopqwop GPTQ/triton and ooba?

#2 opened about 1 year ago by

andysalerno

New activity in junelee/wizard-vicuna-13b about 1 year ago

Prompt Format?

7

#1 opened about 1 year ago by

teknium

New activity in eachadea/ggml-vicuna-13b-1.1 about 1 year ago

ggml-vic13b-uncensored-q5_1.bin and ggml-vic13b-uncensored-q8_0.bin throw errors in newest oobabooga-webui

2

#14 opened about 1 year ago by

RandomLegend

New activity in TheBloke/wizardLM-7B-GGML about 1 year ago

[GUIDE] Launch Q5_1 model with oobabooga's text-generation-webui

5

#5 opened about 1 year ago by

New activity in TheBloke/Vicuna-13B-1.1-GPTQ about 1 year ago

Your converted model performs better, and I don't understand why

#4 opened about 1 year ago by

here is a google colab with 1.1 support

#3 opened about 1 year ago by

eucdee

Cannot load the model

26

#2 opened about 1 year ago by

horstao

New activity in anon8231489123/vicuna-13b-GPTQ-4bit-128g about 1 year ago

do you have 8bit version? with 8bit works better than 4bit?

#13 opened about 1 year ago by

cowboymind

New activity in lmsys/vicuna-13b-v1.1 about 1 year ago

eachadea/vicuna-13b-1.1 vs TheBloke/vicuna-13B-1.1-HF

7

#2 opened about 1 year ago by