Andrei Panferov

#5 opened 5 days ago by

amrothemich

New activity in ISTA-DASLab/Llama-2-7b-AQLM-PV-2Bit-1x16-hf 30 days ago

Create model card

#1 opened 30 days ago by

justheuristic

New activity in Intel/low_bit_open_llm_leaderboard about 1 month ago

Add support for AQLM

3

#1 opened about 2 months ago by

New activity in ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 about 2 months ago

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

#2 opened about 2 months ago by

ubergarm

New activity in ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16 about 2 months ago

Update tokenizer_config.json

#2 opened about 2 months ago by

New activity in ISTA-DASLab/Meta-Llama-3-70B-Instruct-AQLM-2Bit-1x16 about 2 months ago

Update tokenizer_config.json

#1 opened about 2 months ago by

New activity in ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf 3 months ago

ZN2at4_ops15sum_IntList_out4callERKNS_6TensorEN3c1016OptionalArrayRefIlEEbSt8optionalINS5_10ScalarTypeEERS2

9

#3 opened 4 months ago by

LaferriereJC

New activity in ISTA-DASLab/gemma-2b-AQLM-2Bit-1x16-hf 4 months ago

Update README.md

#2 opened 4 months ago by

Updated model description and added evaluation metrics.

#1 opened 4 months ago by

New activity in ISTA-DASLab/gemma-2b-AQLM-2Bit-2x8-hf 4 months ago

Updated description and the metrics

#1 opened 4 months ago by

New activity in ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf 4 months ago

Update README.md

#6 opened 4 months ago by

New activity in ISTA-DASLab/Llama-2-13b-AQLM-2Bit-1x16-hf 4 months ago

Updated 13b model.

#1 opened 4 months ago by

New activity in ISTA-DASLab/Llama-2-7b-AQLM-2Bit-8x8-hf 4 months ago

Upgrade format of this model?

#2 opened 4 months ago by

jaemzfleming

Update README.md

#1 opened 4 months ago by

New activity in ISTA-DASLab/Llama-2-7b-AQLM-2Bit-1x16-hf 4 months ago

Upload finetuned Llama-2-7b models

#1 opened 4 months ago by

New activity in ISTA-DASLab/Llama-2-7b-AQLM-2Bit-2x8-hf 4 months ago

Upload finetuned Llama-2-7b models

#1 opened 4 months ago by

New activity in ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf 4 months ago

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

5

#2 opened 4 months ago by

lxyuan

New activity in ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf 4 months ago

Endpoint encountered an error

#5 opened 4 months ago by

vanokio

New activity in ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf 4 months ago

Update README.md

#1 opened 4 months ago by

New activity in ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf 4 months ago

NameError: name 'flash_attn_func' is not defined

#4 opened 4 months ago by

Neman

New activity in ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf 5 months ago

Cannot test

#1 opened 5 months ago by

andreariboni

Loading Model on AWS G5.4xlarge Instance Results in 'killed' Message

#2 opened 5 months ago by

Tejasram

You are using a model of type mixtral_aqlm to instantiate a model of type mixtral. This is not supported for all configurations of models and can yield errors.

#3 opened 5 months ago by

Tejasram

New activity in BlackSamorez/HuYaLM-100B-fp16 9 months ago

Possible to convert to GGUF?

3

#1 opened 10 months ago by

jackboot

New activity in hf-internal-testing/tiny-random-bloom about 1 year ago

It's not actually random. Many weights are 0 initialized.

#1 opened about 1 year ago by

New activity in BlackSamorez/llama-13b-hf-tensor-parallel over 1 year ago

Example of how to use

3

#1 opened over 1 year ago by

milyiyo

New activity in rinna/japanese-gpt-neox-small over 1 year ago

Update config.json

#1 opened over 1 year ago by