Hugging Face's logo
Wolfram Ravenwolf's picture
TFLOPS icon 72.0 TFLOPS
59 2 132

Wolfram Ravenwolf

wolfram
tomar753's profile picture kaveinthran's profile picture Steelskull's profile picture
·
https://ko-fi.com/wolframravenwolf

AI & ML interests

Local LLMs

Articles

Organizations

Blog-explorers's profile picture

wolfram's activity

New activity in turboderp/Llama-3.1-70B-Instruct-exl2 28 days ago

The tokenizer has changed just fyi

12
#2 opened about 2 months ago by bullerwins
New activity in mistralai/Mistral-7B-Instruct-v0.3 4 months ago

no system message?

8
#14 opened 4 months ago by mclassHF2023

tokenizer.model and tokenizer.model.v3 are identical
#15 opened 4 months ago by wolfram
New activity in nvidia/Llama3-ChatQA-1.5-70B 5 months ago

Concerns regarding Prompt Format

6
#1 opened 5 months ago by wolfram
New activity in wolfram/miquliz-120b-v2.0 6 months ago

Strange observation: model becomes super horny in ST's MinP mode

5
#7 opened 6 months ago by deleted
New activity in wolfram/miquliz-120b-v2.0-GGUF 6 months ago

Upload folder using huggingface_hub

2
#3 opened 6 months ago by wolfram
New activity in wolfram/miquliz-120b-v2.0 6 months ago

VRAM Estimates

6
#3 opened 7 months ago by ernestr

Merge method

1
#4 opened 6 months ago by dnhkng
New activity in wolfram/miqu-1-103b 7 months ago

Can't wait to test

5
#4 opened 7 months ago by froggeric

Kindly asking for quants

7
#2 opened 7 months ago by wolfram
New activity in LoneStriker/miqu-1-103b-3.5bpw-h6-exl2 7 months ago

Update README.md
#1 opened 7 months ago by wolfram
New activity in LoneStriker/miqu-1-103b-3.0bpw-h6-exl2 7 months ago

Update README.md
#1 opened 7 months ago by wolfram
New activity in LoneStriker/miqu-1-103b-2.4bpw-h6-exl2 7 months ago

Update README.md
#1 opened 7 months ago by wolfram
New activity in wolfram/miquliz-120b-v2.0 7 months ago

GPTQ / AWQ

1
#2 opened 7 months ago by agahebr
New activity in wolfram/miqu-1-120b 7 months ago

Guidance on GPU VRAM Split?

5
#3 opened 8 months ago by nmitchko
New activity in wolfram/miqu-1-103b 7 months ago

Upload folder using huggingface_hub

2
#1 opened 7 months ago by wolfram
New activity in wolfram/miquliz-120b-v2.0-3.0bpw-h6-exl2 7 months ago

Very interesting that miqu will give 16k context work even only first layer and last layer

15
#2 opened 7 months ago by akoyaki
New activity in wolfram/miquliz-120b-v2.0-GGUF 7 months ago

iMatrix, IQ2_XS & IQ2_XXS

13
#2 opened 7 months ago by Nexesenex
New activity in wolfram/miqu-1-120b 7 months ago

Performance

13
#2 opened 8 months ago by KnutJaegersberg
New activity in wolfram/miquliz-120b-v2.0-3.0bpw-h6-exl2 7 months ago

VRAM requirements

8
#1 opened 7 months ago by sophosympatheia
New activity in wolfram/miquliz-120b 7 months ago

benchmarks?

1
#1 opened 8 months ago by distantquant
New activity in LoneStriker/miquliz-120b-4.0bpw-h6-exl2 8 months ago

Update README.md
#1 opened 8 months ago by wolfram
New activity in LoneStriker/miquliz-120b-2.9bpw-h6-exl2 8 months ago

Update README.md
#1 opened 8 months ago by wolfram
New activity in LoneStriker/miquliz-120b-2.65bpw-h6-exl2 8 months ago

Update README.md
#1 opened 8 months ago by wolfram
New activity in LoneStriker/miquliz-120b-2.4bpw-h6-exl2 8 months ago

Update README.md
#2 opened 8 months ago by wolfram
New activity in wolfram/miqu-1-120b 8 months ago

Kindly asking for quants

4
#1 opened 8 months ago by wolfram
New activity in LoneStriker/wolfram_miqu-1-120b-GGUF 8 months ago

Update README.md
#1 opened 8 months ago by wolfram
New activity in LoneStriker/wolfram_miqu-1-120b-5.0bpw-h6-exl2 8 months ago

Update README.md
#2 opened 8 months ago by wolfram
New activity in LoneStriker/wolfram_miqu-1-120b-4.0bpw-h6-exl2 8 months ago

Update README.md
#1 opened 8 months ago by wolfram
New activity in LoneStriker/wolfram_miqu-1-120b-3.0bpw-h6-exl2 8 months ago

Update README.md
#1 opened 8 months ago by wolfram
New activity in LoneStriker/wolfram_miqu-1-120b-2.65bpw-h6-exl2 8 months ago

Update README.md
#1 opened 8 months ago by wolfram
New activity in LoneStriker/wolfram_miqu-1-120b-2.4bpw-h6-exl2 8 months ago

Update README.md
#1 opened 8 months ago by wolfram
New activity in LoneStriker/wolfram_miqu-1-120b-5.0bpw-h6-exl2 8 months ago

Update README.md
#1 opened 8 months ago by wolfram
New activity in mlabonne/Beyonder-4x7B-v2 8 months ago

Wrong prompt format in tokenizer_config.json?

3
#7 opened 8 months ago by wolfram
New activity in cognitivecomputations/dolphin-2.6-mistral-7b 9 months ago

UnicodeDecodeError with ooba's Transformers loader

5
#4 opened 9 months ago by wolfram
New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 9 months ago

Instruction Template during inference?

7
#6 opened 9 months ago by jf-11
New activity in DiscoResearch/DiscoLM-120b 9 months ago

Summoning EXL2 version ;)

9
#2 opened 10 months ago by wolfram
New activity in migtissera/Tess-XL-v1.0 10 months ago

Any chance for an EXL2 version?

15
#2 opened 10 months ago by wolfram
New activity in TheBloke/Nous-Capybara-34B-GGUF 10 months ago

Incorrect EOS token

9
#2 opened 10 months ago by Henk717
New activity in TheBloke/dolphin-2_2-yi-34b-GGUF 10 months ago

BOS token as 1 seriously hurts these GGUF Yi models

29
#2 opened 10 months ago by wolfram
New activity in TheBloke/Nous-Capybara-34B-GGUF 10 months ago

BOS token as 1 seriously hurts these GGUF Yi models

11
#1 opened 10 months ago by KerfuffleV2
New activity in cognitivecomputations/dolphin-2.0-mistral-7b 11 months ago

ChatML prompt format confusion - please reconsider

36
#3 opened 12 months ago by kalomaze
New activity in TheBloke/Airoboros-L2-70B-3.1.2-GGUF 11 months ago

Broken model!

1
#1 opened 11 months ago by wolfram
New activity in lizpreciatior/lzlv_70b_fp16_hf 12 months ago

Pretty good

5
#1 opened 12 months ago by Sao10K
New activity in TheBloke/EverythingLM-13B-V3-16K-GGUF 12 months ago

Broken model?

4
#1 opened 12 months ago by wolfram
New activity in migtissera/Synthia-13B-v1.2 12 months ago

Call for quantization

1
#1 opened 12 months ago by wolfram
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/Spicyboros-70B-2.2-GGUF about 1 year ago

spicyboros-70b-2.2.Q4_0.gguf broken as well?

10
#1 opened about 1 year ago by wolfram
New activity in tiiuae/falcon-180B-chat about 1 year ago

RoPE scaling?
#6 opened about 1 year ago by wolfram
New activity in TheBloke/Airoboros-L2-70B-2.1-Creative-GGUF about 1 year ago

airoboros-l2-70b-2.1-creative.Q4_0.gguf broken?
#1 opened about 1 year ago by wolfram
New activity in h2oai/h2ogpt-4096-llama2-13b-chat about 1 year ago

Why is this model the exact same as Llama 2 Chat 13B?

1
#1 opened about 1 year ago by wolfram
New activity in Open-Orca/OpenOrcaxOpenChat-Preview2-13B about 1 year ago

Prompt template discrepancy

4
#4 opened about 1 year ago by wolfram
New activity in jarradh/llama2_70b_chat_uncensored about 1 year ago

Please fix the misleading naming

4
#1 opened about 1 year ago by wolfram
New activity in TheBloke/llama2_70b_chat_uncensored-GGML about 1 year ago

Second time I fell for this... misleading naming.

2
#1 opened about 1 year ago by wolfram
New activity in TheBloke/Hermes-LLongMA-2-13B-8K-GGML about 1 year ago

"How to run in llama.cpp" is for 2048 instead of 8192 context size

2
#1 opened about 1 year ago by wolfram
New activity in TheBloke/Llama-2-13B-chat-GGML about 1 year ago

Extreme levels of censorship?

8
#2 opened about 1 year ago by ceoofcapybaras
New activity in open-llm-leaderboard/open_llm_leaderboard about 1 year ago

Why did top-ranked Guanaco 65B disappear from the leaderboard?

8
#108 opened about 1 year ago by wolfram
New activity in TheBloke/llama-2-13B-German-Assistant-v2-GGML about 1 year ago

Get only empty string '' response back - Anyone used them successfully?

10
#1 opened about 1 year ago by appliedstuff
New activity in AlekseyKorshuk/vicuna-7b over 1 year ago

I made a GPTQ 4bit 128g version of this model

4
#3 opened over 1 year ago by TheBloke