Hugging Face's logo
Rickard Edén's picture
12 16

Rickard Edén

neph1
KBLLR's profile picture 21world's profile picture d2erima's profile picture
·
neph1

AI & ML interests

applying, dataset creation, finetuning, loras

Organizations

Social Post Explorers's profile picture

neph1's activity

New activity in pyp1/VoiceCraft 2 months ago

Safetensors?

1
#3 opened 3 months ago by mo137
New activity in Quant-Cartel/Cerebrum-1.0-8x7b-iMat-GGUF 3 months ago

Smaller IQs performance?

2
#1 opened 3 months ago by neph1
New activity in neph1/bellman-7b-mistral-instruct-v0.2 4 months ago

3B version?

4
#1 opened 5 months ago by Chriffe
New activity in vikhyatk/moondream1 4 months ago

fp32 for everything?

2
#8 opened 4 months ago by neph1
New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 4 months ago

Running a 4-bit Quantized 7B Model on a PC: Feasibility and Insights

4
#109 opened 5 months ago by edw-hug-face
New activity in vikhyatk/moondream1 4 months ago

I'd like to see a GGUF version of this

3
#5 opened 5 months ago by iplayfast
New activity in neph1/bellman-7b-mistral-instruct-v0.2 5 months ago

Unquantized version
#2 opened 5 months ago by neph1
New activity in neph1/stable-diffusion-prompt-pairs 6 months ago

[bot] Conversion to Parquet
#1 opened 6 months ago by parquet-converter
New activity in TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF 6 months ago

Q6_K appears to be broken (And maybe other K-Quants as well)

3
#11 opened 6 months ago by Mikael110

Why is the response slower than the 70B model?

7
#9 opened 6 months ago by shalene

chatbot giving weird responses

20
#6 opened 6 months ago by hammad93
New activity in neph1/Alpaca-Lora-GPT4-Swedish-Refined 8 months ago

[bot] Conversion to Parquet
#1 opened 8 months ago by parquet-converter