Viktor Ferenczi

viktor-ferenczi's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in codellama/CodeLlama-70b-Instruct-hf over 1 year ago

Context length?

13

#2 opened over 1 year ago by

turboderp

New activity in Trelis/Yi-6B-200K-Llamafied-chat-SFT-AWQ over 1 year ago

EOS fine-tuning

2

#1 opened over 1 year ago by

viktor-ferenczi

New activity in NousResearch/Yarn-Llama-2-13b-128k over 1 year ago

Any plans for YaRN CodeLlama?

3

#6 opened over 1 year ago by

viktor-ferenczi

New activity in lmdeploy/llama2-chat-70b-4bit over 1 year ago

llama2-chat-70b-w4 weights

👍 1

2

#1 opened over 1 year ago by

sandrobovelli

New activity in openlm-research/open_llama_7b_v2 almost 2 years ago

Update `README.md`

3

#1 opened almost 2 years ago by

alvarobartt

New activity in Salesforce/xgen-7b-8k-base almost 2 years ago

Error loading model into Test Generation Web UI (ooba)

8

#11 opened almost 2 years ago by

viktor-ferenczi

New activity in TheBloke/WizardLM-Uncensored-Falcon-40B-GPTQ almost 2 years ago

What hardware do I need for reasonable performance?

4

#3 opened almost 2 years ago by

TS0001

New activity in ichitaka/falcon-40b-instruct-8bit almost 2 years ago

Is the snippet in README loading the model in 8-bit mode?

5

#2 opened almost 2 years ago by

mahmoudajawad

New activity in hkunlp/instructor-xl almost 2 years ago

How does the embedding model on code text?

4

#18 opened almost 2 years ago by

chonghao-cc

New activity in TheBloke/guanaco-65B-HF almost 2 years ago

Can't run model

5

#1 opened almost 2 years ago by

mikeytrw