Hugging Face's logo

Cognitive Computations

community
https://erichartford.com
cognitivecompai
ehartford
Activity Feed

AI & ML interests

Supervised Fine Tuning, DPO, and unalignment

Recent Activity

v2ray  new activity 3 days ago
cognitivecomputations/DeepSeek-R1-0528-AWQ:running with flashmla on A100s
ehartford  new activity 4 days ago
cognitivecomputations/DeepSeek-R1-0528-AWQ:running with flashmla on A100s
ehartford  updated a model 4 days ago
cognitivecomputations/DeepSeek-R1-0528-AWQ
View all activity

cognitivecomputations's activity

cfahlgren1 
posted an update 3 days ago
v2ray 
in cognitivecomputations/DeepSeek-R1-0528-AWQ 3 days ago

running with flashmla on A100s

1
#1 opened 4 days ago by
ehartford
ehartford 
in cognitivecomputations/DeepSeek-R1-0528-AWQ 4 days ago

running with flashmla on A100s

1
#1 opened 4 days ago by
ehartford
ehartford 
updated a model 4 days ago
ehartford 
published a model 4 days ago
ehartford 
updated a model 6 days ago
ehartford 
published a model 6 days ago
v2ray 
in cognitivecomputations/DeepSeek-V3-0324-AWQ 10 days ago

could you give me a reason why you ignore kv_a_proj_with_mqa layer when quantizing this model?

1
#10 opened 10 days ago by
superahn
ehartford 
updated a dataset 11 days ago
ehartford 
published a dataset 11 days ago
v2ray 
in cognitivecomputations/Dolphin3.0-Llama3.1-8B-GGUF 12 days ago

gshshdhdhhdididhxbcbdhdudhbdbdbdbehe

4
#3 opened 12 days ago by
MYNK337
cfahlgren1 
posted an update 16 days ago
v2ray 
in cognitivecomputations/DeepSeek-R1-AWQ 19 days ago

H800 has errors

1
#35 opened 21 days ago by
yiyepialing
ehartford 
in cognitivecomputations/dolphin-logger 20 days ago

Add new log files: 4c29dad8-d447-4966-828d-2adb352da70f.jsonl, d1616eff-b581-447d-961b-80833607adf7.jsonl, dffa3c08-5ce7-4580-ba0c-ef6291bd6c56.jsonl, 50cccd8a-e34d-4c91-9971-d35684273b03.jsonl, b74d0306-3679-498a-bd9d-c4fa892f03e1.jsonl
#1 opened 24 days ago by
ehartford

Add new log files from /Users/eric/.dolphin-logger/logs
#2 opened 24 days ago by
ehartford
mahiatlinux 
in cognitivecomputations/Qwen3-30B-A3B-AWQ 23 days ago

Update README.md
#1 opened 23 days ago by
mahiatlinux
mahiatlinux 
in cognitivecomputations/Qwen3-235B-A22B-AWQ 23 days ago

Fixed the code formatting.
#2 opened 23 days ago by
mahiatlinux
ehartford 
published a dataset 24 days ago
ehartford 
in cognitivecomputations/coding-collect 25 days ago

Add new log files: 4c29dad8-d447-4966-828d-2adb352da70f.jsonl, d1616eff-b581-447d-961b-80833607adf7.jsonl, dffa3c08-5ce7-4580-ba0c-ef6291bd6c56.jsonl, 50cccd8a-e34d-4c91-9971-d35684273b03.jsonl, b74d0306-3679-498a-bd9d-c4fa892f03e1.jsonl
#9 opened 25 days ago by
ehartford
ImranzamanML 
posted an update 25 days ago
view post
Post
548
Run LLM model Locally using Docker right inside your codebase (No GUI Needed!)

In this project, I did not used the suporting GUI like Open WebUI or LM Studio or any other, so the purpose to use stand alone LLM models with ollama to give you the idea that how you can use it in your project/code instead of running through third party. Everything is containerized with Docker, so setup is clean and repeatable. Its just a fun side project so my connections can learn more about running models locally in their own projects.

Tech stack used:

🐋 Docker

🦙 LLaMA via Ollama

💻 HTML/CSS/JS

🐍 Python + FastAPI

🌐 NGINX



Its still early and a fun side project, but if you are into local model deployment, or just want to see how it works, check it out on the given link!

https://github.com/Imran-ml/llama-chatbot-dockerized

#LLM #Docker #OpenSource #Chatbot #LLaMA #fastapi