RichardErkhov/Telugu-LLM-Labs_-_Indic-gemma-2b-finetuned-sft-Navarasa-2.0-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Indic-gemma-2b-finetuned-sft-Navarasa-2.0 - GGUF

• —Model creator: https://huggingface.co/Telugu-LLM-Labs/
• —Original model: https://huggingface.co/Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0/

Original model description: --- license: other licensename: gemma-terms-of-use licenselink: https://ai.google.dev/gemma/terms base_model: google/gemma-2b datasets:

• —ravithejads/samvaad-hi-filtered
• —Telugu-LLM-Labs/telugutekniumGPTeachergeneralinstructfilteredromanized
• —Telugu-LLM-Labs/telugualpacayahmacleanedfiltered_romanized
• —Telugu-LLM-Labs/sindhialpacayahmacleanedfiltered
• —Telugu-LLM-Labs/urdualpacayahmacleanedfiltered
• —Telugu-LLM-Labs/marathialpacayahmacleanedfiltered
• —Telugu-LLM-Labs/assamesealpacayahmacleanedfiltered
• —Telugu-LLM-Labs/konkanialpacayahmacleanedfiltered
• —Telugu-LLM-Labs/nepalialpacayahmacleanedfiltered
• —abhinand/tamil-alpaca
• —Tensoic/airoboros-3.2_kn
• —Tensoic/gpt-teacher_kn
• —VishnuPJ/AlpacaInstructMalayalam
• —Tensoic/Alpaca-Gujarati
• —HydraIndicLM/punjabialpaca52K
• —HydraIndicLM/bengalialpacadolly_67k
• —OdiaGenAI/OdiaAlpacainstructions_52k
• —yahma/alpaca-cleaned language:
• —te
• —en
• —ta
• —ml
• —mr
• —hi
• —kn
• —sd
• —ne
• —ur
• —as
• —gu
• —bn
• —pa
• —or libraryname: transformers pipelinetag: text-generation ---

Indic-gemma-2b-finetuned-sft-Navarasa-2.0

This model is based on google/gemma-2b and hase been LoRA finetuned on 15 Indian languages and English language instruction datasets:

1. 1.#### Hindi - ravithejads/samvaad-hi-filtered, HydraIndicLM/hindi_alpaca_dolly_67k(sampled)
2. 2.#### Telugu - Telugu-LLM-Labs/telugu_alpaca_yahma_cleaned_filtered_romanized, Telugu-LLM-Labs/telugu_teknium_GPTeacher_general_instruct_filtered_romanized
3. 3.#### Marathi - Telugu-LLM-Labs/sindhi_alpaca_yahma_cleaned_filtered
4. 4.#### Urdu - Telugu-LLM-Labs/urdu_alpaca_yahma_cleaned_filtered
5. 5.#### Assamese - Telugu-LLM-Labs/assamese_alpaca_yahma_cleaned_filtered
6. 6.#### Konkani - Telugu-LLM-Labs/konkani_alpaca_yahma_cleaned_filtered
7. 7.#### Nepali - Telugu-LLM-Labs/nepali_alpaca_yahma_cleaned_filtered
8. 8.#### Sindhi - Telugu-LLM-Labs/sindhi_alpaca_yahma_cleaned_filtered
9. 9.#### Tamil - abhinand/tamil-alpaca
10. 10.#### Kannada - Tensoic/airoboros-3.2_kn, Tensoic/gpt-teacher_kn
11. 11.#### Malayalam - VishnuPJ/Alpaca_Instruct_Malayalam
12. 12.#### Gujarati - Tensoic/Alpaca-Gujarati
13. 13.#### Punjabi - HydraIndicLM/punjabi_alpaca_52K
14. 14.#### Bengali - HydraIndicLM/bengali_alpaca_dolly_67k(alpaca filtered)
15. 15.#### Odia - OdiaGenAI/Odia_Alpaca_instructions_52k, OdiaGenAI/gpt-teacher-roleplay-odia-3k
16. 16.#### English - yahma/alpaca-cleaned

The model is finetuned using unsloth library and we provide inference code using the same for faster inference. Alternatively you can use HuggingFace Library for inference.

Training Details:

The model is trained on approx 650K instruction samples.

1. 1.GPU: 1 A100, 80GB
2. 2.Time: 45 Hours
3. 3.Platform: E2E Networks

Installation

!pip install -U xformers --index-url https://download.pytorch.org/whl/cu121 !pip install "unsloth[kaggle-new] @git+https://github.com/unslothai/unsloth.git@nightly"

Input Text Format

### Instruction: {instruction}

### Input: {input}

## Response: {response}

Inference With Unsloth

from unsloth import FastLanguageModel
import torch
max_seq_length = 2048
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = False 
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0",
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
    device_map="auto"
)
FastLanguageModel.for_inference(model) # Enable native 2x faster inference

input_prompt = """
### Instruction:
{}

### Input:
{}

### Response:
{}"""

input_text = input_prompt.format(
        "Tranlsate following sentence to Hindi.", # instruction
        "India is a great country.", # input
        "", # output - leave this blank for generation!
    )

inputs = tokenizer([input_text], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 300, use_cache = True)
response = tokenizer.batch_decode(outputs)

Inference with HuggingFace

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model = AutoModelForCausalLM.from_pretrained(
    "Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0",
    load_in_4bit = False,
    token = hf_token
)
model.to("cuda")

tokenizer = AutoTokenizer.from_pretrained("Telugu-LLM-Labs/Indic-gemma-2b-finetuned-sft-Navarasa-2.0")

input_prompt = """
### Instruction:
{}

### Input:
{}

### Response:
{}"""

input_text = input_prompt.format(
        "Tranlsate following sentence to Hindi.", # instruction
        "India is a great country.", # input
        "", # output - leave this blank for generation!
    )

inputs = tokenizer([input_text], return_tensors = "pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens = 300, use_cache = True)
response = tokenizer.batch_decode(outputs)[0]

Refer to the blog post for sample examples.

Please check our Code Repository for training and inference scripts.

Developers:

The model is a collaborative effort by Ravi Theja and Ramsri Goutham. Feel free to DM either of us if you have any questions.