monsoon-nlp/tomatotomato-gLM2-150M-v0.1
Fill-Mask ā¢ 0.2B ā¢ Updated ā¢ 4
Nick Doiron
monsoon-nlp
AI & ML interests
biology and multilingual models
Recent Activity
reacted to pankajpandey-dev's post with š„ 3 days ago
š®š³ Qwen3-4B Hindi Instruct v2 ā a Hindi LLM that runs on your own machine
Most strong Hindi-capable models are either huge or cloud-only. I wanted one that's small enough to run locally but actually follows instructions in Hindi ā so I fine-tuned Qwen3-4B on 10K Hindi instruction pairs and shipped it with a full GGUF quant ladder.
ā
Fine-tune (16-bit): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2
ā
GGUF (Q4/Q5/Q8): huggingface.co/pankajpandey-dev/Qwen3-4B-Hindi-Instruct-v2-GGUF
Runs in Ollama, llama.cpp, and LM Studio. The Q4_K_M is just 2.5 GB ā fits comfortably on a laptop, CPU or GPU.
Part of my Hindi LLM Series ā building openly-licensed Indic models for local and edge use. More coming (Gemma next). Feedback welcome š
#Hindi #IndicNLP #GGUF #LocalLLM #Qwen
liked a model 3 days ago
biohub/ESMC-6B liked a model 3 days ago
biohub/ESMFold2Organizations
monsoon-nlp/dna-blockdiff-2
Fill-Mask ā¢ 98.7M ā¢ Updated ā¢ 12
monsoon-nlp/dna-blockdiff-papaya
Fill-Mask ā¢ 98.7M ā¢ Updated ā¢ 10 ā¢ 1
monsoon-nlp/dna-blockdiff
Fill-Mask ā¢ 98.7M ā¢ Updated ā¢ 9
monsoon-nlp/gpt-nyc-nontoxic
Text Generation ā¢ 0.1B ā¢ Updated ā¢ 12
monsoon-nlp/dv-muril
Fill-Mask ā¢ 0.2B ā¢ Updated ā¢ 15
monsoon-nlp/dv-labse
Fill-Mask ā¢ 0.5B ā¢ Updated ā¢ 27
monsoon-nlp/byt5-basque
0.3B ā¢ Updated ā¢ 8
monsoon-nlp/byt5-dv
0.3B ā¢ Updated ā¢ 10
monsoon-nlp/dv-wave
13.4M ā¢ Updated ā¢ 15 ā¢ 1
monsoon-nlp/byt5-base-dv
0.7B ā¢ Updated ā¢ 8
monsoon-nlp/bangla-electra
13.5M ā¢ Updated ā¢ 94 ā¢ 5
monsoon-nlp/codellama-abliterated-2xd
Text Generation ā¢ 7B ā¢ Updated ā¢ 6
monsoon-nlp/codellama-abliterated
Text Generation ā¢ 7B ā¢ Updated ā¢ 4 ā¢ 1
monsoon-nlp/protein-matryoshka-embeddings
Sentence Similarity ā¢ 0.4B ā¢ Updated ā¢ 12 ā¢ 6
monsoon-nlp/llama3-biotoken3pretrain-kaniwa
Updated ā¢ 2
monsoon-nlp/llama3-biotokenpretrain-kaniwa
Updated ā¢ 1
monsoon-nlp/llama3-dnapretrain-kaniwa
Updated
monsoon-nlp/tinyllama-mixpretrain-uniprottune
Updated ā¢ 3
monsoon-nlp/nyc-savvy-llama2-7b-lora-adapter
Updated
monsoon-nlp/tinyllama-mixpretrain-quinoa-sciphi
Text Generation ā¢ 1B ā¢ Updated ā¢ 5
monsoon-nlp/tinyllama-proteinpretrain-quinoa
Text Generation ā¢ 1B ā¢ Updated ā¢ 4
monsoon-nlp/BioMedGPT-16bit
Text Generation ā¢ 7B ā¢ Updated ā¢ 3
monsoon-nlp/gpt-nyc-small
Text Generation ā¢ 0.1B ā¢ Updated ā¢ 8
monsoon-nlp/eyegazer-vit-binary
Updated ā¢ 10 ā¢ 1
monsoon-nlp/eyegazer-vit-lora
Updated ā¢ 5
monsoon-nlp/mGPT-quantized
Text Generation ā¢ 1B ā¢ Updated ā¢ 737 ā¢ 1
monsoon-nlp/hindi-bert
Feature Extraction ā¢ 14.7M ā¢ Updated ā¢ 539 ā¢ 20
monsoon-nlp/tamillion
Feature Extraction ā¢ 0.1B ā¢ Updated ā¢ 17 ā¢ 3
monsoon-nlp/nyrkr-joker-llama
Text Generation ā¢ Updated ā¢ 6 ā¢