Hugging Face's logo
Eric Hartford's picture
37 1

Eric Hartford

erichartford
bemer12's profile picture jbethea's profile picture phi0112358's profile picture
·

AI & ML interests

None yet

Recent Activity

new activity about 16 hours ago
cognitivecomputations/SexDrugsAndRockAndRoll:Issues with the dataset
new activity 3 days ago
arcee-ai/DeepSeek-V3-0324-bf16:Update modeling_deepseek.py
updated a model 6 days ago
erichartford/gemma-3-1b-it-abliterated-mlx-8Bit
View all activity

Organizations

Lazarus AI R&D's profile picture LZR Valence's profile picture lzr-intel's profile picture ericjasonjorge's profile picture

erichartford's activity

New activity in cognitivecomputations/SexDrugsAndRockAndRoll about 16 hours ago

Issues with the dataset

1
#4 opened 3 days ago by
SicariusSicariiStuff
New activity in arcee-ai/DeepSeek-V3-0324-bf16 3 days ago

Update modeling_deepseek.py
#2 opened 3 days ago by
erichartford
New activity in mlabonne/gemma-3-1b-it-abliterated 6 days ago

Thanks!

1
#1 opened 6 days ago by
erichartford
New activity in mlabonne/gemma-3-4b-it-abliterated 7 days ago

1b?

1
#1 opened 7 days ago by
erichartford
New activity in mlabonne/dolphin-r1-deepseek 8 days ago

Confirm the data is generated with the 670B deepseek-R1 or smaller distilled R1 model

2
#2 opened 8 days ago by
donniems
New activity in google/gemma-3-27b-it 8 days ago

evals (PT vs IT)

1
#30 opened 8 days ago by
erichartford
New activity in mlabonne/gemma-3-27b-it-abliterated 9 days ago

Method

4
#4 opened 10 days ago by
erichartford
New activity in Qwen/Qwen2.5-VL-72B-Instruct 14 days ago

official finetune example?

2
#16 opened 27 days ago by
erichartford
New activity in mlx-community/DeepSeek-R1-qm_4_2 15 days ago

What is this one
#1 opened 15 days ago by
erichartford
New activity in Qwen/QwQ-32B 22 days ago

recommended generation parameters

6
#5 opened 22 days ago by
erichartford
New activity in unsloth/Qwen2.5-VL-72B-Instruct 27 days ago

difference from Qwen/Qwen2.5-VL-72B-Instruct

2
#2 opened 27 days ago by
erichartford
New activity in neuralmagic/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic about 1 month ago

Update tokenizer_config.json

5
#3 opened about 1 month ago by
erichartford

<think>

1
#2 opened about 1 month ago by
erichartford
New activity in mlabonne/natural_reasoning-formatted about 1 month ago

License

1
#1 opened about 1 month ago by
erichartford
New activity in facebook/natural_reasoning about 1 month ago

Update README.md

1
#3 opened about 1 month ago by
erichartford
New activity in jondurbin/cinematika-v0.1 about 1 month ago

jsonl

4
#3 opened 12 months ago by
ehartford
New activity in AlSamCur123/NotDolphin3.0-Llama3.1-8 about 1 month ago

Please rename

2
#1 opened about 1 month ago by
erichartford
New activity in hirundo-io/DeepSeek-R1-Distill-Llama-8B-Debiased about 2 months ago

Hirundo’s bias unlearning capabilities

2
#1 opened about 2 months ago by
ehartford
New activity in mistralai/Mistral-Small-24B-Instruct-2501 about 2 months ago

updated model_max_length from to 1000000000000000019884624838656 to 32768

2
#21 opened about 2 months ago by
LHC88
New activity in unsloth/DeepSeek-R1-BF16 2 months ago

how did you create it?

1
#1 opened 2 months ago by
erichartford