Kai Howard

New activity in totally-not-an-llm/PuddleJumper-13b-V2 5 months ago

Adding Evaluation Results

#3 opened 10 months ago by

New activity in totally-not-an-llm/EverythingLM-13b-V2-16k 5 months ago

Adding Evaluation Results

#2 opened 10 months ago by

New activity in totally-not-an-llm/EverythingLM-13b-16k 5 months ago

Adding Evaluation Results

#1 opened 10 months ago by

New activity in totally-not-an-llm/PuddleJumper-13b-V2 11 months ago

Mistral-7B version

#2 opened 11 months ago by

Apel-sin

New activity in totally-not-an-llm/EveryPHIngLM-1.3b-V3 11 months ago

Training script

#1 opened 11 months ago by

nulltella

New activity in totally-not-an-llm/EverythingLM-13b-V3-16k 12 months ago

How does the automatically triggered CoT reasoning work?

#1 opened 12 months ago by

afg1

New activity in totally-not-an-llm/EverythingLM-13b-V3-peft 12 months ago

Librarian Bot: Add base_model information to model

#1 opened 12 months ago by

librarian-bot

New activity in totally-not-an-llm/EverythingLM-13b-peft 12 months ago

Librarian Bot: Add base_model information to model

#1 opened 12 months ago by

librarian-bot

New activity in totally-not-an-llm/PuddleJumper-13b 12 months ago

PuddleJumper is one of my favorite models. Plans for 30B version?

#3 opened 12 months ago by

ttkciar

New activity in totally-not-an-llm/PuddleJumper-13b about 1 year ago

Adapter Merge Details

#2 opened about 1 year ago by

polymer

Meh~

#1 opened about 1 year ago by

krasavello2011

New activity in totally-not-an-llm/AlpacaCielo-13b about 1 year ago

Merging technique

#3 opened about 1 year ago by

khoantap

New activity in totally-not-an-llm/EverythingLM-13b-V2-16k about 1 year ago

Fine tuning

4

#1 opened about 1 year ago by

viren-takia

New activity in bhenrym14/airophin-13b-pntk-16k-fp16 about 1 year ago

QLoRa model?

#2 opened about 1 year ago by

New activity in totally-not-an-llm/EverythingLM-data about 1 year ago

Is this a LLM generated dataset or curated from the internet?

#2 opened about 1 year ago by

Sunny111

New activity in totally-not-an-llm/AlpacaCielo-13b about 1 year ago

7b model.

7

#2 opened about 1 year ago by

Herman555

New activity in totally-not-an-llm/EverythingLM-data about 1 year ago

Does the relatively less number of samples affect downstream finetuning?

3

#1 opened about 1 year ago by

ritabratamaiti

New activity in totally-not-an-llm/AlpacaCielo2-7b-8k about 1 year ago

How did you merge the models?

2

#2 opened about 1 year ago by

Vezora

New activity in s3nh/totally-not-an-llm-AlpacaCielo2-7b-8k-GPTQ about 1 year ago

Have you got it to work?

3

#1 opened about 1 year ago by

New activity in totally-not-an-llm/AlpacaCielo2-7b-8k about 1 year ago

Questions about model

8

#1 opened about 1 year ago by

Tibbnak

New activity in totally-not-an-llm/AlpacaCielo-13b about 1 year ago

further quants

4

#1 opened about 1 year ago by

IkariDev

New activity in cognitivecomputations/dolphin-llama-13b about 1 year ago

Base model?

#2 opened about 1 year ago by

New activity in chargoddard/llama2-22b about 1 year ago

More info?

6

#1 opened about 1 year ago by

New activity in cognitivecomputations/dolphin about 1 year ago

Would building a model under Apache 2.0 license with this dataset violate OpenAI terms of service?

5

#5 opened about 1 year ago by

kishb87

New activity in Henk717/airochronos-33B about 1 year ago

Why weight avg instead of lora merge?

4

#1 opened about 1 year ago by

New activity in jondurbin/airoboros-7b-gpt4-1.2 about 1 year ago

Unmerged lora model?

#1 opened about 1 year ago by