Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix Add Support For Following Models By SarvamAI [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
ollama/ollama#14688•Fetched 2026-04-08 00:32:53
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Author
MeetSolanki530MeetSolanki530
Participants
MeetSolanki530MeetSolanki530
Timeline (top)
closed ×1
RAW_BUFFERClick to expand / collapse

🚀 Model Request: Add Sarvam AI Models to Ollama

Model Repository

Model Overview

Sarvam AI provides multilingual large language models optimized for Indian languages and reasoning tasks. These models support a wide range of Indic languages including Hindi, Gujarati, Tamil, Telugu, Kannada, and Marathi while maintaining strong English performance.

Adding Sarvam models to Ollama would enable developers to run Indic-focused LLMs locally, which is currently an underserved area in open-source LLM tooling.

Why This Model Should Be Added

  • Strong Indic language support
  • Useful for local AI applications in India
  • Good performance on reasoning, multilingual tasks, and coding
  • Growing ecosystem around Sarvam AI models
  • Expands Ollama’s coverage beyond primarily English-centric models

Potential Use Cases

  • Multilingual assistants for Indian users
  • Government and enterprise document processing
  • Regional language chatbots
  • Translation and cross-lingual workflows
  • Education and accessibility tools

Suggested Model Variants

ModelDescription
sarvam-1Lightweight model for local deployment
sarvam-mMid-size multilingual model
sarvam-30bLarge high-performance model
sarvam-105bEnterprise-scale model

Technical Details

  • Organization: Sarvam AI
  • Architecture: Transformer / Mixture-of-Experts (larger variants)
  • Language Support: English + Indic languages (Hindi, Gujarati, Tamil, Telugu, Kannada, Marathi, etc.)
  • License: (As specified in the HuggingFace repositories)

Additional Notes

If required, the models could be converted to GGUF format for llama.cpp compatibility, allowing them to run efficiently through Ollama.

Adding Sarvam models would significantly improve regional language support within the Ollama ecosystem.

extent analysis

Fix Plan

To add Sarvam AI models to Ollama, follow these steps:

  • Convert the Sarvam AI models to GGUF format for compatibility with llama.cpp.
  • Update the Ollama model repository to include the converted Sarvam AI models.
  • Modify the Ollama configuration to support the new models.

Example code for converting a model to GGUF format:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the Sarvam AI model and tokenizer
model_name = "sarvamai/sarvam-1"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Convert the model to GGUF format
# ... (implementation details depend on the specific conversion tool)

# Save the converted model
torch.save(model.state_dict(), "sarvam-1-gguf.pth")

Verification

To verify that the fix worked:

  • Run the Ollama application with the updated model repository.
  • Test the Sarvam AI models using the Ollama API.
  • Check the model performance on Indic language tasks.

Extra Tips

  • Ensure that the converted models are compatible with the Ollama ecosystem.
  • Test the models thoroughly to ensure they work as expected.
  • Consider adding additional support for Indic languages in the Ollama application.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#ssr#installation#tensor shape#autograd error#dependency error#configuration error#environment variable#network issue#logging issue

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING