James Edward

#1 opened 3 months ago by

New activity in bardsai/jaskier-7b-dpo-v6.1 5 months ago

GGUF?

#1 opened 5 months ago by

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

I need general help with setting up or using system prompts or templates in Oobabooga. Please help someone.

#7 opened 7 months ago by

New activity in cognitivecomputations/dolphin-2.1-mistral-7b 7 months ago

I can only get this to work at 8192 context? In Oobabooga. I heard it could do more? Is that false?

2

#12 opened 9 months ago by

New activity in TheBloke/openchat_3.5-GGUF 7 months ago

I really need help with Templates? How to interpret and use them?

#5 opened 9 months ago by

New activity in open-llm-leaderboard/open_llm_leaderboard 8 months ago

NEW! OpenLLMLeaderboard 2023 fall update

20

#356 opened 9 months ago by

clefourrier

New activity in TheBloke/dolphin-2.2.1-mistral-7B-GGUF 9 months ago

The best model

#1 opened 9 months ago by

Kenshiro-28

New activity in TheBloke/llava-v1.5-13B-GPTQ 9 months ago

No GGUF Quatization?

6

#1 opened 9 months ago by

New activity in cognitivecomputations/dolphin-2.1-mistral-7b 9 months ago

In Oobabooga what Instruction template do I select for Dolphin Mistral 2.1?

#11 opened 9 months ago by

New activity in TheBloke/dolphin-2.1-mistral-7B-GGUF 10 months ago

dolphin-2.1-mistral-7B is even better than openorca-mistral-7b unbelievable

#1 opened 10 months ago by

mirek190

New activity in TheBloke/storytime-13B-GGUF 10 months ago

Quick question is this a 2048 or 4096 model for context size in Ooba? Using Ctransformers?

#1 opened 10 months ago by

New activity in TheBloke/guanaco-33B-GGML 11 months ago

Is it possible to make this exact model in GGUF?

#4 opened 11 months ago by

New activity in TheBloke/WizardLM-1.0-Uncensored-Llama2-13B-GGML 12 months ago

was unable to load using text-generation-webui

#1 opened 12 months ago by

LaferriereJC

New activity in TheBloke/llama2_70b_chat_uncensored-GGML 12 months ago

Uncensored my ass ....

#2 opened 12 months ago by

mirek190

New activity in jarradh/llama2_70b_chat_uncensored 12 months ago

So this model can't or should not be used in Instruct mode? That's my favorite mode I think.

#2 opened 12 months ago by

New activity in TheBloke/Guanaco-33B-SuperHOT-8K-GGML 12 months ago

Will this work at 4K or 8K context in oobabooga yet?

#2 opened 12 months ago by

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

How long does it take to run these tests?

#90 opened about 1 year ago by

New activity in TheBloke/minotaur-15B-GGML about 1 year ago

Getting this to run in Ooba? Anyone know what settings I have to choose?

#3 opened about 1 year ago by

New activity in TheBloke/Wizard-Vicuna-30B-Uncensored-GGML about 1 year ago

I can't get GGML GPU accelleration to work with Wizard-Vicuna-30B 5_1?

10

#3 opened about 1 year ago by

New activity in TheBloke/Nous-Hermes-13B-GPTQ about 1 year ago

Is it only 3 tokens per second?

#2 opened about 1 year ago by

mcian91

New activity in TheBloke/guanaco-33B-GGML about 1 year ago

Using CPU only

#1 opened about 1 year ago by

BBLL3456

New activity in reeducator/vicuna-13b-cocktail about 1 year ago

Great triton-4bit-128g.safetensors is giving me giberish?

#6 opened about 1 year ago by

New activity in OccamRazor/mpt-7b-storywriter-4bit-128g about 1 year ago

Oobabooga Error einops import rearrange ModuleNotFoundError: No module named 'einops' Press any key to continue . . .

#1 opened about 1 year ago by

New activity in reeducator/vicuna-13b-cocktail about 1 year ago

Sorry Triton VS Cuda what is the difference?

#4 opened about 1 year ago by

New activity in reeducator/vicuna-13b-free about 1 year ago

The V4 is here

80

#11 opened over 1 year ago by

TheYuriLover

Question about The roles are still USER and ASSISTANT. Early stopping tokens bug.

#24 opened about 1 year ago by

v230502 Testing and Discussion

89

#23 opened about 1 year ago by deleted

V4.3 Early Testing.

109

#15 opened about 1 year ago by deleted

Do I just copy over the config, tokenizer_config, and tokenizer.model from another 13B Vicuna Model to get this working in ooba? I am getting error.

10

#17 opened about 1 year ago by

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

Responses stop loading in.

2

#42 opened about 1 year ago by

Setphus

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

Censored or uncensored?

11

#6 opened over 1 year ago by

New activity in TheBloke/gpt4-alpaca-lora-30B-GGML about 1 year ago

These are all censored models?

#3 opened about 1 year ago by

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

Will a 1.1-uncensored follow?

#11 opened over 1 year ago by

Wubbbi

New activity in MetaIX/GPT4-X-Alpaca-30B-4bit about 1 year ago

Error: Internal: src/sentencepiece_processor.cc in Ooba and KAI 4bit

4

#8 opened over 1 year ago by

Co0ode

New activity in Thireus/Vicuna13B-v1.1-8bit-128g about 1 year ago

Censored or not?

#2 opened over 1 year ago by

New activity in elinas/alpaca-30b-lora-int4 over 1 year ago

How to get this running on Oobabooga with RTX 4080 16GB?

8

#17 opened over 1 year ago by