Dr. Nicefellow
DrNicefellow
AI & ML interests
LLM and AGI. Sometimes, play with Diffusion models
Recent Activity
new activity
about 1 month ago
deepseek-ai/DeepSeek-R1-0528:Summer or Winter?
new activity
about 1 month ago
Qwen/Qwen2.5-Omni-7B-GPTQ-Int4:Any engine for real time speech to speech chat with this?
new activity
about 2 months ago
DrNicefellow/Microscopic-Mistral-18k-steps:Adding `safetensors` variant of this model
Organizations
-
DrNicefellow/CHAT-ALL-IN-ONE-v1
Viewer • Updated • 1.24M • 72 • 5 -
DrNicefellow/ChatAllInOne-Yi-34B-200K-V1
Text Generation • 34B • Updated • 28 • 8 -
DrNicefellow/ChatAllInOne-Mistral-7B-V1
Text Generation • 7B • Updated • 19 • 1 -
DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1
Text Generation • Updated • 13
-
DrNicefellow/Microscopic-Mistral-3k-steps
Text Generation • Updated • 15 -
DrNicefellow/Microscopic-Mistral-6k-steps
Text Generation • Updated • 26 -
DrNicefellow/Microscopic-Mistral-12k-steps
Text Generation • Updated • 17 -
DrNicefellow/Microscopic-Mistral-18k-steps
Text Generation • 0.8B • Updated • 38
-
DrNicefellow/microscopic-mamba-2.1B-hf-1.0ksteps
Text Generation • Updated • 50 -
DrNicefellow/microscopic-mamba-2.1B-hf-7.8ksteps
Text Generation • Updated • 21 -
DrNicefellow/microscopic-mamba-2.1B-hf-4.9ksteps
Text Generation • Updated • 62 -
DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps
Text Generation • Updated • 20
-
DrNicefellow/Qwen1.5-72B-Chat-5bpw-exl2
Text Generation • Updated • 80 -
DrNicefellow/Qwen1.5-72B-Chat-2.2bpw-exl2
Text Generation • Updated • 20 • 1 -
DrNicefellow/Qwen1.5-72B-Chat-4.65bpw-exl2
Text Generation • Updated • 15 -
DrNicefellow/Qwen1.5-72B-Chat-3.2bpw-exl2
Text Generation • Updated • 15
-
DrNicefellow/Mistral-1-from-Mixtral-8x7B-v0.1
Text Generation • 7B • Updated • 23 • 1 -
DrNicefellow/Mistral-2-from-Mixtral-8x7B-v0.1
Text Generation • 7B • Updated • 19 -
DrNicefellow/Mistral-3-from-Mixtral-8x7B-v0.1
Text Generation • 7B • Updated • 50 -
DrNicefellow/Mistral-4-from-Mixtral-8x7B-v0.1
Text Generation • 7B • Updated • 23
-
DrNicefellow/Microscopic-Olmo-2B-1.1k-steps
Text Generation • Updated • 55 -
DrNicefellow/Microscopic-Olmo-2B-3.9k-steps
Text Generation • Updated • 11 -
DrNicefellow/Microscopic-Olmo-2B-7.2k-steps
Text Generation • Updated • 11 -
DrNicefellow/Microscopic-Olmo-2B-11.8k-steps
Text Generation • Updated • 16
-
DrNicefellow/Nano-GPT2-500m-29k_steps-ChatAllInOne_step-5000
Text Generation • 0.5B • Updated • 25 -
DrNicefellow/Nano-GPT2-500m-29k_steps-ChatAllInOne_step-2500
Text Generation • 0.5B • Updated • 14 -
DrNicefellow/Nano-GPT2-500m-29k_steps
Text Generation • 0.5B • Updated • 17 -
meta-llama/Llama-3.1-8B
Text Generation • 8B • Updated • 890k • • 1.67k
A friendly reminder: change the max_seq_len in text-generation-web-ui, otherwise, you get CUDA outta memory.
-
DrNicefellow/Mistral-Nemo-Instruct-2407-exl2-4bpw
Text Generation • Updated • 25 • 1 -
DrNicefellow/Mistral-Nemo-Instruct-2407-exl2-5bpw
Text Generation • Updated • 15 -
DrNicefellow/Mistral-Nemo-Instruct-2407-exl2-8bpw-h8
Text Generation • Updated • 15 • 6 -
DrNicefellow/Mistral-Nemo-Instruct-2407-exl2-4.5bpw
Text Generation • Updated • 16
-
DrNicefellow/CHAT-ALL-IN-ONE-v1
Viewer • Updated • 1.24M • 72 • 5 -
DrNicefellow/ChatAllInOne-Yi-34B-200K-V1
Text Generation • 34B • Updated • 28 • 8 -
DrNicefellow/ChatAllInOne-Mistral-7B-V1
Text Generation • 7B • Updated • 19 • 1 -
DrNicefellow/ChatAllInOne_Mixtral-8x7B-v1
Text Generation • Updated • 13
-
DrNicefellow/Mistral-1-from-Mixtral-8x7B-v0.1
Text Generation • 7B • Updated • 23 • 1 -
DrNicefellow/Mistral-2-from-Mixtral-8x7B-v0.1
Text Generation • 7B • Updated • 19 -
DrNicefellow/Mistral-3-from-Mixtral-8x7B-v0.1
Text Generation • 7B • Updated • 50 -
DrNicefellow/Mistral-4-from-Mixtral-8x7B-v0.1
Text Generation • 7B • Updated • 23
-
DrNicefellow/Microscopic-Mistral-3k-steps
Text Generation • Updated • 15 -
DrNicefellow/Microscopic-Mistral-6k-steps
Text Generation • Updated • 26 -
DrNicefellow/Microscopic-Mistral-12k-steps
Text Generation • Updated • 17 -
DrNicefellow/Microscopic-Mistral-18k-steps
Text Generation • 0.8B • Updated • 38
-
DrNicefellow/Microscopic-Olmo-2B-1.1k-steps
Text Generation • Updated • 55 -
DrNicefellow/Microscopic-Olmo-2B-3.9k-steps
Text Generation • Updated • 11 -
DrNicefellow/Microscopic-Olmo-2B-7.2k-steps
Text Generation • Updated • 11 -
DrNicefellow/Microscopic-Olmo-2B-11.8k-steps
Text Generation • Updated • 16
-
DrNicefellow/microscopic-mamba-2.1B-hf-1.0ksteps
Text Generation • Updated • 50 -
DrNicefellow/microscopic-mamba-2.1B-hf-7.8ksteps
Text Generation • Updated • 21 -
DrNicefellow/microscopic-mamba-2.1B-hf-4.9ksteps
Text Generation • Updated • 62 -
DrNicefellow/microscopic-mamba-2.1B-hf-13.4ksteps
Text Generation • Updated • 20
-
DrNicefellow/Nano-GPT2-500m-29k_steps-ChatAllInOne_step-5000
Text Generation • 0.5B • Updated • 25 -
DrNicefellow/Nano-GPT2-500m-29k_steps-ChatAllInOne_step-2500
Text Generation • 0.5B • Updated • 14 -
DrNicefellow/Nano-GPT2-500m-29k_steps
Text Generation • 0.5B • Updated • 17 -
meta-llama/Llama-3.1-8B
Text Generation • 8B • Updated • 890k • • 1.67k
-
DrNicefellow/Qwen1.5-72B-Chat-5bpw-exl2
Text Generation • Updated • 80 -
DrNicefellow/Qwen1.5-72B-Chat-2.2bpw-exl2
Text Generation • Updated • 20 • 1 -
DrNicefellow/Qwen1.5-72B-Chat-4.65bpw-exl2
Text Generation • Updated • 15 -
DrNicefellow/Qwen1.5-72B-Chat-3.2bpw-exl2
Text Generation • Updated • 15
A friendly reminder: change the max_seq_len in text-generation-web-ui, otherwise, you get CUDA outta memory.
-
DrNicefellow/Mistral-Nemo-Instruct-2407-exl2-4bpw
Text Generation • Updated • 25 • 1 -
DrNicefellow/Mistral-Nemo-Instruct-2407-exl2-5bpw
Text Generation • Updated • 15 -
DrNicefellow/Mistral-Nemo-Instruct-2407-exl2-8bpw-h8
Text Generation • Updated • 15 • 6 -
DrNicefellow/Mistral-Nemo-Instruct-2407-exl2-4.5bpw
Text Generation • Updated • 16