Hugging Face's logo
Andrei Panferov's picture
32 4 3

Andrei Panferov

BlackSamorez
Ai11Ali's profile picture fullstack's profile picture Azik's profile picture
·

AI & ML interests

NLP

Recent Activity

updated a model 8 days ago
daslab-testing/QuEST-100M-BF16-400X
updated a collection 8 days ago
QuEST
published a model 8 days ago
daslab-testing/QuEST-100M-BF16-400X
View all activity

Organizations

IST Austria Distributed Algorithms and Systems Lab's profile picture ISTA DASLab Testing Account's profile picture

BlackSamorez's activity

New activity in ISTA-DASLab/QuEST-800M-INT4 about 1 month ago

Add metadata
#1 opened about 1 month ago by
nielsr
New activity in ISTA-DASLab/Llama-3.3-70B-Instruct-HIGGS-4bit 4 months ago

how do you load it?

3
#1 opened 4 months ago by
KnutJaegersberg
New activity in ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 9 months ago

Repetitive generation without additional EOS token

2
#5 opened 9 months ago by
amrothemich
New activity in ISTA-DASLab/Llama-2-7b-AQLM-PV-2Bit-1x16-hf 10 months ago

Create model card
#1 opened 10 months ago by
justheuristic
New activity in Intel/low_bit_open_llm_leaderboard 10 months ago

Add support for AQLM

3
#1 opened 11 months ago by
BlackSamorez
New activity in ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 11 months ago

~8 tok/sec with ~5k context on vLLM with Flash Attention and `kv_cache_dtype="fp8"` on 3090TI 24GB VRAM

2
#2 opened 11 months ago by
ubergarm
New activity in ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16 11 months ago

Update tokenizer_config.json
#2 opened 11 months ago by
BlackSamorez
New activity in ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 11 months ago

Update tokenizer_config.json
#1 opened 11 months ago by
BlackSamorez
New activity in ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf about 1 year ago

ZN2at4_ops15sum_IntList_out4callERKNS_6TensorEN3c1016OptionalArrayRefIlEEbSt8optionalINS5_10ScalarTypeEERS2

9
#3 opened about 1 year ago by
LaferriereJC
New activity in ISTA-DASLab/gemma-2b-AQLM-2Bit-1x16-hf about 1 year ago

Update README.md

1
#2 opened about 1 year ago by
SpiridonSunRotator

Updated model description and added evaluation metrics.

1
#1 opened about 1 year ago by
SpiridonSunRotator
New activity in ISTA-DASLab/gemma-2b-AQLM-2Bit-2x8-hf about 1 year ago

Updated description and the metrics
#1 opened about 1 year ago by
SpiridonSunRotator
New activity in ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf about 1 year ago

Update README.md
#6 opened about 1 year ago by
SpiridonSunRotator
New activity in ISTA-DASLab/Llama-2-13b-AQLM-2Bit-1x16-hf about 1 year ago

Updated 13b model.
#1 opened about 1 year ago by
SpiridonSunRotator
New activity in ISTA-DASLab/Llama-2-7b-AQLM-2Bit-8x8-hf about 1 year ago

Upgrade format of this model?

2
#2 opened about 1 year ago by
jaemzfleming

Update README.md
#1 opened about 1 year ago by
SpiridonSunRotator
New activity in ISTA-DASLab/Llama-2-7b-AQLM-2Bit-1x16-hf about 1 year ago

Upload finetuned Llama-2-7b models

1
#1 opened about 1 year ago by
SpiridonSunRotator
New activity in ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf about 1 year ago

Upload finetuned Llama-2-7b models

1
#1 opened about 1 year ago by
SpiridonSunRotator
New activity in ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf about 1 year ago

Loading Error: BlackSamorez/Mixtral-8x7B-Instruct-v0.1-AQLM-2Bit-1x16-hf Model in Colab

5
#2 opened about 1 year ago by
lxyuan
New activity in ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf about 1 year ago

Endpoint encountered an error

2
#5 opened about 1 year ago by
vanokio