Hugging Face's logo
Martial Terran's picture
35 3

Martial Terran

MartialTerran
Corianas's profile picture rahulganju's profile picture Roya90's profile picture
·

AI & ML interests

I, Martial Terran am leading a Group to build solar-powered TimeCapsuleTeacher(TM} GPT-powered laptop computers, to provide Language, Math and Science Education to Non-English-Speaking people of the future in a Post-Apophis World.

Recent Activity

updated a model about 12 hours ago
MartialTerran/Method_for_Dynamically_Reducing_Logit_Computation_in_LLMs
New activity about 12 hours ago
Qwen/Qwen2.5-Coder-1.5B
updated a dataset 4 days ago
MartialTerran/Korean_Faces

Organizations

TimeCapsuleTeacherLLM's profile picture

MartialTerran's activity

New activity in Qwen/Qwen2.5-Coder-1.5B about 12 hours ago

Optimizing Qwen Coder Models (1.5B & 3B) for Python and Edge Deployment
#6 opened about 12 hours ago by MartialTerran
New activity in roneneldan/TinyStories 7 days ago

Duplicates in Train set

1
#12 opened about 1 year ago by Qilex
New activity in Corianas/llama-tiny-reactor 7 days ago

Storing Spelling information in LLMs

2
#2 opened 14 days ago by MartialTerran
New activity in roneneldan/TinyStories 8 days ago

Cleaned data

3
#15 opened 11 months ago by ad8e
New activity in Qwen/Qwen2.5-Coder-1.5B 10 days ago

Request Fork with Modifications for Python GenAI App Development on Microsoft OS
#5 opened 10 days ago by MartialTerran
New activity in HuggingFaceTB/SmolLM2-360M-Instruct 18 days ago

finetuning

3
#2 opened 22 days ago by HassanStar
New activity in HuggingFaceTB/SmolLM2-1.7B 18 days ago

Using Adapter/PEFT for finetuning a Subnet extracted from the SmolLM2 for Arduino Tool Calling

1
#7 opened 18 days ago by MartialTerran

Extracting an optimized Arduino Tool-Calling Subnet from the SmolLM2 model.
#6 opened 18 days ago by MartialTerran

Extracting subnets from the published SmolLM2 model for compute-efficient task performance on edge devices
#5 opened 18 days ago by MartialTerran

Porting SmolLM2 to Arduino

1
#4 opened 18 days ago by MartialTerran

Pure C++ version of the SmolLM2 model code for EDGE implementations
#3 opened 18 days ago by MartialTerran

Pure Python version for local Inference operation on PC
#2 opened 18 days ago by MartialTerran
New activity in Corianas/Microllama_Char_100k_step 6 months ago

Can Huggingface facilitate experimentation with Tiny LLMs

5
#2 opened 6 months ago by MartialTerran
New activity in unclecode/tinyllama-function-call-Q4_K_M_GGFU-250424 6 months ago

Link to the Python Script or C-compiled Code to Inference-mode run the Model checkpoint?
#1 opened 6 months ago by MartialTerran
New activity in TinyLlama/TinyLlama-1.1B-Chat-v1.0 7 months ago

Too much Junk vocab words in the vocab.json.

8
#28 opened 8 months ago by MartialTerran
New activity in Corianas/Microllama_Char_100k_step 7 months ago

The only used vocabulary words/tokens in this model are the letters of the alphabet?

26
#1 opened 8 months ago by MartialTerran
New activity in calum/tinystories-gpt2-3M 7 months ago

GPT-2 model having16 4-float attention heads
#2 opened 7 months ago by MartialTerran

Performance oddities of the 3M model.
#3 opened 7 months ago by MartialTerran
New activity in Corianas/Microllama_Char_200k_step 8 months ago

Model Has Some Coherence. But only uses single-letter tokens?

1
#2 opened 8 months ago by MartialTerran
New activity in roneneldan/TinyStories 8 months ago

Mismatched Vocab.json verus Words actually within the

6
#19 opened 8 months ago by MartialTerran