David Golchinfar PRO
DavidGF
AI & ML interests
finetune llms, improve german language understanding and generated text of llms
Organizations
DavidGF's activity
Enforcing German model output
3
#4 opened 11 days ago
by
razzfazz-io
spectrum yaml
4
#3 opened about 1 month ago
by
DeepMount00
wrong context length??
1
#6 opened about 2 months ago
by
AaronFeng753
Error when deploying with Inference Endpoints
1
#1 opened about 2 months ago
by
edgelesssys
Incorrect ifeval benchmark
7
#879 opened 2 months ago
by
DavidGF
Update config.yml
#1 opened about 2 months ago
by
DavidGF
Model evaluations failed
4
#884 opened 2 months ago
by
DavidGF
Add base_model metadata
#1 opened about 2 months ago
by
davanstrien
Questions on MMLU
3
#1 opened 3 months ago
by
jphme
very powerful 8b model
1
#3 opened 3 months ago
by
danielplominski
Submission of models
1
#1 opened 3 months ago
by
DavidGF
Reproducabiliy of Evaluation
1
#1 opened 3 months ago
by
DRXD1000
RuntimeError
3
#1 opened 3 months ago
by
mhollomey
'Running' from the first day of the new leaderboard to pending and not showing anymore
1
#845 opened 3 months ago
by
DavidGF
Congrats to the new leaderboard! Accidentally uploaded the wrong modeltype.
4
#794 opened 4 months ago
by
DavidGF
Update VAGOsolutions/SauerkrautLM-SOLAR-Instruct_eval_request_False_bfloat16_Original.json
#15 opened 4 months ago
by
DavidGF
Update VAGOsolutions/SauerkrautLM-Qwen-32b_eval_request_False_bfloat16_Original.json
#14 opened 4 months ago
by
DavidGF
Update VAGOsolutions/SauerkrautLM-SOLAR-Instruct_eval_request_False_bfloat16_Original.json
#13 opened 4 months ago
by
DavidGF
Update VAGOsolutions/SauerkrautLM-Qwen-32b_eval_request_False_bfloat16_Original.json
#12 opened 4 months ago
by
DavidGF
Update VAGOsolutions/SauerkrautLM-Mixtral-8x7B-Instruct_eval_request_False_bfloat16_Original.json
#11 opened 4 months ago
by
DavidGF
Update VAGOsolutions/SauerkrautLM-Gemma-7b_eval_request_False_bfloat16_Original.json
#10 opened 4 months ago
by
DavidGF
Update VAGOsolutions/SauerkrautLM-Gemma-2b_eval_request_False_bfloat16_Original.json
#9 opened 4 months ago
by
DavidGF
Update VAGOsolutions/SauerkrautLM-7b-LaserChat_eval_request_False_bfloat16_Original.json
#8 opened 4 months ago
by
DavidGF
Update VAGOsolutions/SauerkrautLM-7b-HerO_eval_request_False_bfloat16_Original.json
#7 opened 4 months ago
by
DavidGF
Update VAGOsolutions/SauerkrautLM-1.5b_eval_request_False_bfloat16_Original.json
#6 opened 4 months ago
by
DavidGF
Update VAGOsolutions/Llama-3-SauerkrautLM-70b-Instruct_eval_request_False_bfloat16_Original.json
#5 opened 4 months ago
by
DavidGF
Context window
2
#4 opened 6 months ago
by
tapos999
Llama-3 70b model eval failed and can't submit again
16
#709 opened 6 months ago
by
DavidGF
How to setup model parameters and prompt format in HF Chat-UI?
1
#3 opened 6 months ago
by
PaulForsterNewman
Update README.md
1
#3 opened 5 months ago
by
NeuralNovel
quantized versions
2
#1 opened 6 months ago
by
Tdot123
Clarification needed and request for GGUF support for llama.cpp?
1
#6 opened 6 months ago
by
rboehme86
Dataset used to fine-tune on
1
#1 opened 6 months ago
by
jdjayakaran2410
GSM8K: which value will be selected?
3
#682 opened 6 months ago
by
DavidGF
Upload tokenizer.json
#1 opened 6 months ago
by
Kearm
Context/Input length of the Model
2
#1 opened 7 months ago
by
kreabs
Function calling format
10
#3 opened 7 months ago
by
RangerMauve
Model resubmit after wrong dtype used
1
#616 opened 8 months ago
by
DavidGF
Update README.md
3
#13 opened 8 months ago
by
DavidGF
Deepseak Laser possible?
7
#2 opened 9 months ago
by
Venkman42
License - commercial use
2
#5 opened 9 months ago
by
pepperscene
How to properly prompt the model for instruction tasks
7
#2 opened 9 months ago
by
martinkozle
System Prompt to improve responses in German language
6
#6 opened 9 months ago
by
ThiloteE
Awesome- Could you help with pointers on doing same for Other languages(Swedish)?
3
#2 opened 10 months ago
by
Olofp
Doesn't follow instruction very well
4
#3 opened 10 months ago
by
andreP
This model is the actual first model that feels like gpt4 to me.
4
#1 opened 10 months ago
by
dillfrescott
Quants uploading now
1
#4 opened 10 months ago
by
TheBloke
There seems to be a problem with the mixtral finetuning evaluations
9
#491 opened 10 months ago
by
DavidGF
Update README.md
#1 opened 10 months ago
by
DavidGF
QLora or full fine-tuning?
1
#1 opened 10 months ago
by
SamuelAzran
Add merge tag
#4 opened 10 months ago
by
davanstrien
[FLAG] fblgit/una-xaberius-34b-v1beta
125
#444 opened 10 months ago
by
XXXGGGNEt
Training dataset + Hyperparamters
2
#1 opened 11 months ago
by
Viewegger
Adding `safetensors` variant of this model
#2 opened 11 months ago
by
SFconvertbot