Hugging Face's logo
None's picture
51 107

None

Thireus
·

AI & ML interests

None yet

Organizations

None yet

Thireus's activity

New activity in bartowski/Qwen2.5-72B-Instruct-exl2 1 day ago

5.5 bits and 6bits per weight?
#1 opened 1 day ago by Thireus
New activity in mattshumer/Reflection-Llama-3.1-70B 4 days ago

CORRECTION: THIS SYSTEM MESSAGE IS ***PURE GOLD***!!!

16
#33 opened 13 days ago by jukofyork
New activity in Kijai/flux-fp8 about 2 months ago

FP8 Checkpoint version size mismatch?

2
#15 opened about 2 months ago by Thireus
New activity in meta-llama/Meta-Llama-3-70B-Instruct 5 months ago

What is the "system" prompt?

3
#13 opened 5 months ago by kk3dmax
New activity in mistralai/Mixtral-8x22B-Instruct-v0.1 5 months ago

First Word Ignored Issue / Single Word Instruction

20
#11 opened 5 months ago by pandora-s

Prompt format

1
#12 opened 5 months ago by Thireus
New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 5 months ago

Incomplete Answers

7
#59 opened 9 months ago by samparksoftwares
New activity in turboderp/Mixtral-8x22B-Instruct-v0.1-exl2 5 months ago

Weird answers for short instructions such as "Hi"?
#2 opened 5 months ago by Thireus
New activity in mistral-community/Mixtral-8x22B-v0.1 5 months ago

Instruct version?

4
#13 opened 5 months ago by Thireus
New activity in cognitivecomputations/dolphin-2.5-mixtral-8x7b 9 months ago

Higher PPL than Mixtral?

3
#11 opened 9 months ago by Thireus
New activity in LoneStriker/dolphin-2.2-70b-6.0bpw-h6-exl2 9 months ago

exl2-2 please?

8
#1 opened 9 months ago by Thireus
New activity in cognitivecomputations/dolphin-2.2-70b 10 months ago

Safetensors version?

6
#2 opened 11 months ago by matatonic
New activity in cognitivecomputations/dolphin-2_2-yi-34b 10 months ago

Casual system prompts give very bad results
#7 opened 10 months ago by Thireus
New activity in LoneStriker/dolphin-2.2-yi-34b-4.0bpw-h6-exl2 10 months ago

tokenization_yi.py

6
#1 opened 10 months ago by Stilgar
New activity in cognitivecomputations/dolphin-2_2-yi-34b 10 months ago

No need to trust_remote_code

1
#6 opened 10 months ago by Weyaxi
New activity in cognitivecomputations/dolphin-2.2-70b 10 months ago

Orca 2 upgrade planned?

1
#6 opened 10 months ago by Thireus
New activity in Panchovix/goliath-120b-exl2 10 months ago

3bpw not working anymore

6
#1 opened 10 months ago by mpasila
New activity in cognitivecomputations/dolphin-2.2-70b 11 months ago

Keep up the good work!

3
#3 opened 11 months ago by Thireus

exl2 quanitzed version

3
#1 opened 11 months ago by Thireus
New activity in jondurbin/airoboros-l2-c70b-3.1.2 11 months ago

Any positive results so far?

1
#1 opened 11 months ago by Thireus
New activity in WizardLMTeam/WizardLM-70B-V1.0 11 months ago

Any plans for V1.1?

1
#17 opened 11 months ago by Thireus
New activity in LoneStriker/zephyr-7b-beta-8.0bpw-h6-exl2 11 months ago

h8 instead of h6 for 8bpw versions

1
#1 opened 11 months ago by Thireus
New activity in cognitivecomputations/dolphin-2.2.1-mistral-7b 11 months ago

Really impressive!

15
#1 opened 11 months ago by Thireus
New activity in Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors about 1 year ago

Update bin2safetensors/convert.py
#2 opened about 1 year ago by Thireus
New activity in simsim314/WizardLM-70B-V1.0-HF about 1 year ago

Script used to convert the original model
#1 opened about 1 year ago by Thireus
New activity in Panchovix/airoboros-l2-70b-gpt4-1.4.1-safetensors about 1 year ago

Update bin2safetensors/convert.py

1
#1 opened about 1 year ago by Thireus
New activity in Panchovix/airoboros-l2-70b-gpt4-1.4.1_5.0bpw-h6-exl2 about 1 year ago

Convertion process

3
#1 opened about 1 year ago by Thireus
New activity in uni-tianyan/Uni-TianYan about 1 year ago

Prompt format?

1
#3 opened about 1 year ago by Thireus
New activity in fangloveskari/ORCA_LLaMA_70B_QLoRA about 1 year ago

Prompt format?

1
#9 opened about 1 year ago by Thireus
New activity in migtissera/Synthia-70B-v1.2 about 1 year ago

I wonder what is the difference between version 1.1 and 1.2

16
#2 opened about 1 year ago by Flanua
New activity in TheBloke/StableBeluga2-70B-GPTQ about 1 year ago

GGML version possible/coming?

2
#8 opened about 1 year ago by Thireus
New activity in cognitivecomputations/WizardLM-33B-V1.0-Uncensored about 1 year ago

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

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

Best parameters for 24GB VRAM?

1
#2 opened about 1 year ago by Thireus

Prompt format?

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

Prompt format?

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

Prompt format?

5
#1 opened about 1 year ago by Thireus
New activity in MetaIX/GPT4-X-Alpasta-30b over 1 year ago

Excellent model - Any plans for further finetuning and/or 65b?
#6 opened over 1 year ago by Thireus
New activity in open-llm-leaderboard/open_llm_leaderboard over 1 year ago

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

1
#43 opened over 1 year ago by Thireus
New activity in TheBloke/falcon-40b-instruct-GPTQ over 1 year ago

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

11
#1 opened over 1 year ago by Suoriks
New activity in TheBloke/guanaco-65B-GPTQ over 1 year ago

You're blazing fast!

9
#1 opened over 1 year ago by Thireus
New activity in TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ over 1 year ago

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

7
#2 opened over 1 year ago by andysalerno
New activity in junelee/wizard-vicuna-13b over 1 year ago

Prompt Format?

7
#1 opened over 1 year ago by teknium
New activity in eachadea/ggml-vicuna-13b-1.1 over 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 over 1 year ago by RandomLegend
New activity in TheBloke/wizardLM-7B-GGML over 1 year ago

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

5
#5 opened over 1 year ago by Thireus
New activity in TheBloke/Vicuna-13B-1.1-GPTQ over 1 year ago

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

3
#4 opened over 1 year ago by Thireus

here is a google colab with 1.1 support

6
#3 opened over 1 year ago by eucdee

Cannot load the model

26
#2 opened over 1 year ago by horstao
New activity in anon8231489123/vicuna-13b-GPTQ-4bit-128g over 1 year ago

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

3
#13 opened over 1 year ago by cowboymind
New activity in lmsys/vicuna-13b-v1.1 over 1 year ago

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

7
#2 opened over 1 year ago by Thireus