Indian Flag
Government Of India
A-
A
A+
UpvoteUpvote
0

SmolLM2-135M-Constitutional-ChitChat-v1-F16-GGUF

A lightweight SmolLM2 135M conversational language model fine tuned on the Constitutional AI ChitChat dataset for empathetic helpful and natural dialogue. Optimized for lightweight local conversational AI applications.
  • Upvotes0upvotes
  • Downloads6downloads
  • Views148views
  • File size229.67 MB
  • Shares0Shares
  • Last updatedupdated 07 Jul 2026
UpvoteUpvote
0
LICENSE Apache 2.0
SECTOR Governance and Administration

About Model

SmolLM2 135M Constitutional ChitChat v1 is a fine tuned conversational language model built on the SmolLM2 135M Instruct base model. The model was fine tuned using the Chitchat Constitutional AI dataset with QLoRA to improve conversational quality empathy and instruction following while maintaining a lightweight footprint. The model is intended for friendly conversations casual dialogue emotional support style interactions and general conversational assistance. After fine tuning the model was merged with the base model converted to GGUF format and validated for local inference using llama cpp. Key Features Lightweight 135M parameter model Fine tuned using Constitutional AI ChitChat dataset QLoRA based parameter efficient fine tuning GGUF compatible Suitable for local CPU and GPU inference Optimized for conversational AI Limitations The model is not intended for factual question answering advanced reasoning mathematical problem solving or coding assistance. It may generate inaccurate factual information and should not be used for high risk applications requiring guaranteed correctness.

Metadata Metadata

Apache 2.0

Governance and Administration

Shlok Pankaj Salunke

N.A.

Shlok Salunke

N.A.

N.A.

N.A.

N.A.

N.A.

N.A.

N.A.

Open

27/06/26 14:41:18

N.A.

229.67 MB

Tags

  • chatbot
  • Conversational AI
  • Dialogue
  • LLM Fine-tuning
  • LLM

Linked Dataset Linked Dataset

Chitchat Constitutional AI
Chitchat Constitutional AI
3.8Information•Updated 9 month(s) ago
FACEBOOK INDIA ONLINE SERVICES PRIVATE LIMITED
  • See Upvoters0
  • Downloads18
  • Views232
  • File Size107.86 MB


Related Models Related Models

RAG Engine
Python script that implements a Retrieval‑Augmented Generation (RAG) pipeline for document question answering.
Text Generation
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views23
  • File Size0

tokenmodel
How people read your model before they download it.
Transformers
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views1
  • File Size0

AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views3
  • File Size0

Samadhan-Bharat-Epoch1-Tri-Statutory-Neural-Model
Sovereign 5-Head Tri-Statutory Deep Neural Engine integrating 22 Indic constitutional languages, MSMED Act Section 16 monthly compounding (3x RBI rate), CGST Section 16(2)(b) statutory delivery estoppel, Section 43B(h) Income Tax profit disallowances, and RBI CRILC delinquency classification.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads2
  • Views36
  • File Size584.43 KB

Samadhan-Bharat-Sovereign-Indic-Voice-RVC-Acoustic-Engine
Deep neural acoustic adjudication and Retrieval-Based Voice Conversion (RVC) engine trained on IndiaAI cloud infrastructure. Features 1,976,327 trainable parameters with a 4-layer LayerNorm SiLU backbone and multi-head statutory predictors. Simultaneously predicts invoice default principal, statutory delay horizon, Section 16 monthly compound interest (at 3x RBI Bank Rate), and 4-quadrant legal classification from 256-D vernacular speech feature tensors across India's 22 scheduled languages.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads1
  • Views41
  • File Size2.41 MB

Samadhan-Bharat-Sovereign-4Quadrant-2B-Master-Engine
Sovereign 4-Quadrant Dual-Pincer neural engine for simultaneous MSME delayed trade liquidity unfreezing and GST circular trading fraud detection, trained and validated over 1.35 Trillion statutory transactions.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views37
  • File Size44.73 KB

Samadhan-Bharat-Sovereign-Dual-Head-Model
Dual-head sovereign legal AI model trained on IndiaAI AIRAWAT and 16-Core CPU supercluster across 15.7M+ tokens. Features a 95.04% accurate Judicial Adjudication Head for Section 18 MSMED disputes and a 100.00% accurate Treasury Anti-Fraud Head for circular GST invoice interception.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads1
  • Views58
  • File Size55.94 KB

Mizomade-Mizo-EN-NLLB-S1
Fine-tuned pre trained model for Mizo-English machine translation, trained on Mizo-English parallel datasets to improve translation performance for the Mizo language.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads2
  • Views69
  • File Size1.18 GB

Test model
Model Short Description
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views1
  • File Size65 Bytes

NCERT-TUTOR-v3
NCERT-aligned tutor LoRA for on-device K-12 tutoring. Runs on 4 GB VRAM (RTX 3050). Stage-3 chained adapter: 15.7k curated questions (Grades 6-12, 13 subjects) + 3 DPO stages (math reasoning, mined factuality, multi-subject). 58% on held-out NCERT math with worked steps.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads5
  • Views211
  • File Size65.36 MB


Related Models by Organization Related Models by Organization

RAG Engine
Python script that implements a Retrieval‑Augmented Generation (RAG) pipeline for document question answering.
Text Generation
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views23
  • File Size0

tokenmodel
How people read your model before they download it.
Transformers
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views1
  • File Size0

AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views3
  • File Size0

Samadhan-Bharat-Epoch1-Tri-Statutory-Neural-Model
Sovereign 5-Head Tri-Statutory Deep Neural Engine integrating 22 Indic constitutional languages, MSMED Act Section 16 monthly compounding (3x RBI rate), CGST Section 16(2)(b) statutory delivery estoppel, Section 43B(h) Income Tax profit disallowances, and RBI CRILC delinquency classification.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads2
  • Views36
  • File Size584.43 KB

Samadhan-Bharat-Sovereign-Indic-Voice-RVC-Acoustic-Engine
Deep neural acoustic adjudication and Retrieval-Based Voice Conversion (RVC) engine trained on IndiaAI cloud infrastructure. Features 1,976,327 trainable parameters with a 4-layer LayerNorm SiLU backbone and multi-head statutory predictors. Simultaneously predicts invoice default principal, statutory delay horizon, Section 16 monthly compound interest (at 3x RBI Bank Rate), and 4-quadrant legal classification from 256-D vernacular speech feature tensors across India's 22 scheduled languages.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads1
  • Views41
  • File Size2.41 MB

Samadhan-Bharat-Sovereign-4Quadrant-2B-Master-Engine
Sovereign 4-Quadrant Dual-Pincer neural engine for simultaneous MSME delayed trade liquidity unfreezing and GST circular trading fraud detection, trained and validated over 1.35 Trillion statutory transactions.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views37
  • File Size44.73 KB

Samadhan-Bharat-Sovereign-Dual-Head-Model
Dual-head sovereign legal AI model trained on IndiaAI AIRAWAT and 16-Core CPU supercluster across 15.7M+ tokens. Features a 95.04% accurate Judicial Adjudication Head for Section 18 MSMED disputes and a 100.00% accurate Treasury Anti-Fraud Head for circular GST invoice interception.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads1
  • Views58
  • File Size55.94 KB

Test model
Model Short Description
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views1
  • File Size65 Bytes

NCERT-TUTOR-v3
NCERT-aligned tutor LoRA for on-device K-12 tutoring. Runs on 4 GB VRAM (RTX 3050). Stage-3 chained adapter: 15.7k curated questions (Grades 6-12, 13 subjects) + 3 DPO stages (math reasoning, mined factuality, multi-subject). 58% on held-out NCERT math with worked steps.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads5
  • Views211
  • File Size65.36 MB

Kaveri-4B
Kaveri-4B is a multilingual text-generation model for conversational AI, instruction following, reasoning, coding assistance, summarization, translation, and general-purpose NLP tasks.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads0
  • Views51
  • File Size7.51 GB


Related Models by Sector Related Models by Sector

Mizomade-Mizo-EN-NLLB-S1
Fine-tuned pre trained model for Mizo-English machine translation, trained on Mizo-English parallel datasets to improve translation performance for the Mizo language.
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads2
  • Views69
  • File Size1.18 GB


Related Models by Task Type Related Models by Task Type

NCERT-TUTOR-v3
NCERT-aligned tutor LoRA for on-device K-12 tutoring. Runs on 4 GB VRAM (RTX 3050). Stage-3 chained adapter: 15.7k curated questions (Grades 6-12, 13 subjects) + 3 DPO stages (math reasoning, mined factuality, multi-subject). 58% on held-out NCERT math with worked steps.
AIKOSH OPENSOURCE COMMUNITY
  • See Upvoters0
  • Downloads5
  • Views211
  • File Size65.36 MB

SPRING-INX-DATA2VEC-AQC-GUJARATI
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads4
  • Views65
  • File Size3.52 GB

SPRING-INX-DATA2VEC-AQC-HINDI
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads2
  • Views75
  • File Size3.53 GB

SPRING-INX-DATA2VEC-AQC-MANIPURI
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads2
  • Views47
  • File Size3.52 GB

SPRING-INX-DATA2VEC-AQC-ASSAMESE
Automatic Speech Recognition (ASR) model for speech recognition, processing audio and transcribing spoken content into text.The inference code, installation requirements, and usage instructions are available in the SPRING Lab, IIT Madras GitHub repository: https://github.com/Speech-Lab-IITM/Fairseq-Inference
DIGITAL INDIA BHASHINI DIVISION
  • See Upvoters0
  • Downloads3
  • Views55
  • File Size3.52 GB

KisanSLM-Gemma3n-E2B-GGUF
This is a zipped GGUF. Download and unzip the file. KisanSLM is a compact domain-specific language model for agricultural advisory in India. Fine-tuned on the Kisan Call Center (KCC) dataset, it learns from millions of farmer queries and expert responses on crops, pests, soil, irrigation, and fertilizers. Designed for low-resource environments, KisanSLM can run on edge devices and supports multilingual queries, enabling farmers to receive timely, practical guidance even in low-connectivity rural
THINK EVOLVE LABS
  • See Upvoters0
  • Downloads22
  • Views175
  • File Size3.02 GB

KisanSLM-Llama3-2-1B-GGUF
This is a zipped GGUF. Download and unzip the file. KisanSLM is a compact domain-specific language model for agricultural advisory in India. Fine-tuned on the Kisan Call Center (KCC) dataset, it learns from millions of farmer queries and expert responses on crops, pests, soil, irrigation, and fertilizers. Designed for low-resource environments, KisanSLM can run on edge devices and supports multilingual queries, enabling farmers to receive timely, practical guidance even in low-connectivity rural
THINK EVOLVE LABS
  • See Upvoters0
  • Downloads23
  • Views221
  • File Size1.47 GB

KisanSLM-LMF2-5-1-2B-GGUF
This is a zipped GGUF. Download and unzip the file. KisanSLM is a compact domain-specific language model for agricultural advisory in India. Fine-tuned on the Kisan Call Center (KCC) dataset, it learns from millions of farmer queries and expert responses on crops, pests, soil, irrigation, and fertilizers. Designed for low-resource environments, KisanSLM can run on edge devices and supports multilingual queries, enabling farmers to receive timely, practical guidance even in low-connectivity rural
THINK EVOLVE LABS
  • See Upvoters0
  • Downloads11
  • Views125
  • File Size682.81 MB

KisanSLM-Qwen3-1-7b-GGUF
This is a zipped fine tune of Qwen3 1.7b model. KisanSLM is a compact domain-specific language model for agricultural advisory in India. Fine-tuned on the Kisan Call Center (KCC) dataset, it learns from millions of farmer queries and expert responses on crops, pests, soil, irrigation, and fertilizers. Designed for low-resource environments, KisanSLM can run on edge devices and supports multilingual queries, enabling farmers to receive timely, practical guidance even in low-connectivity rural
THINK EVOLVE LABS
  • See Upvoters0
  • Downloads20
  • Views211
  • File Size2.55 GB

KisanSLM
KisanSLM is a compact domain-specific language model for agricultural advisory in India. Fine-tuned on the Kisan Call Center (KCC) dataset, it learns from millions of farmer queries and expert responses on crops, pests, soil, irrigation, and fertilizers. Designed for low-resource environments, KisanSLM can run on edge devices and supports multilingual queries, enabling farmers to receive timely, practical guidance even in low-connectivity rural settings.
THINK EVOLVE LABS
  • See Upvoters0
  • Downloads141
  • Views1,085
  • File Size150.77 MB