Rainbow-AI-Specialist is a custom multi-domain fine-tuned AI model based on google/gemma-2-2b-it, trained using QLoRA via Hugging Face TRL (SFTTrainer).
Model Card
By Herish Kondeti, published under apache-2.0, revision 2306306a9460.
Rainbow-AI-Specialist is a custom multi-domain fine-tuned AI model based on google/gemma-2-2b-it, trained using QLoRA via Hugging Face TRL (SFTTrainer). You can load and test this adapter easily in Python using PEFT and Transformers: import torch from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel modelid = "google/gemma-2-2b-it" tokenizer = AutoTokenizer.frompretrained(modelid) basemodel = AutoModelForCausalLM.frompretrained(modelid, torchdtype=torch.float16, devicemap="auto") model = PeftModel.frompretrained(basemodel, "RainbowLord/Rainbow-AI-Specialist") inputs = tokenizer("### User: Write a Python script for a simple trading bot.\n### Rainbow:"…
Read Herish Kondeti's full model card
Rainbow-AI-Specialist
Rainbow-AI-Specialist is a custom multi-domain fine-tuned AI model based on google/gemma-2-2b-it, trained using QLoRA via Hugging Face TRL (SFTTrainer).
Domains Covered
- Python Coding: Clean scripts and algorithmic logic.
- Trading Strategies: Market analysis and financial breakdowns.
- Poetry: Creative and rhythmic writing.
- Nova Persona: Unique character interactions and dialogue.
How to Use
You can load and test this adapter easily in Python using PEFT and Transformers:
```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel
Load base model and tokenizer
model_id = "google/gemma-2-2b-it" tokenizer = AutoTokenizer.from_pretrained(model_id) base_model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
Attach your custom Rainbow adapter!
model = PeftModel.from_pretrained(base_model, "RainbowLord/Rainbow-AI-Specialist")
Test generation
inputs = tokenizer("### User: Write a Python script for a simple trading bot.\n### Rainbow:", return_tensors="pt").to("cuda") outputs = model.generate(**inputs, max_new_tokens=150) print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Identity and Version
- Repository
- RainbowLord/Rainbow-AI-Specialist-MLC
- Publisher
- Herish Kondeti
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- trl, sft
- Revision
- 2306306a9460989410bc5ae107449b3dc938e4ed
- First published
- 2026-09-06
- Last updated
- 2026-09-18
Files and Weights
27 files, 1.8 GB in total. The weights are 19 files totalling 1.8 GB in bin.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| params_shard_0.bin | Weights | 294.9 MB | 2c46222eef61 |
| params_shard_1.bin | Weights | 67.4 MB | 0c570d7495a0 |
| params_shard_10.bin | Weights | 75.7 MB | b471a2335379 |
| params_shard_11.bin | Weights | 75.7 MB | d04207c679bd |
| params_shard_12.bin | Weights | 67.7 MB | 262fe11fa1a0 |
| params_shard_13.bin | Weights | 75.7 MB | 0a33ac3a323b |
| params_shard_14.bin | Weights | 75.7 MB | eedc23ab1e57 |
| params_shard_15.bin | Weights | 67.7 MB | 04177613f2a1 |
| params_shard_16.bin | Weights | 75.7 MB | 9dac950887b2 |
| params_shard_17.bin | Weights | 308.2 MB | 2e388f05d87c |
| params_shard_18.bin | Weights | 36.9 MB | 383dbe086c9e |
| params_shard_2.bin | Weights | 75.7 MB | d76daddff2ab |
| params_shard_3.bin | Weights | 67.7 MB | 0abc4791d964 |
| params_shard_4.bin | Weights | 75.7 MB | 1a3027b66a78 |
| params_shard_5.bin | Weights | 75.7 MB | 51ee5c1a9eae |
| params_shard_6.bin | Weights | 67.7 MB | 8024eea5191d |
| params_shard_7.bin | Weights | 75.7 MB | c4725ff02970 |
| params_shard_8.bin | Weights | 75.7 MB | fff04a20ae65 |
| params_shard_9.bin | Weights | 67.7 MB | 48e4102843b1 |
| mlc-chat-config.json | Configuration | 368 B | — |
| ndarray-cache.json | Configuration | 123.1 KB | — |
| README.md | Documentation | 1.4 KB | — |
| chat_template.jinja | Other | 591 B | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer.json | Tokenizer | 34.4 MB | 487cee872421 |
| tokenizer.model | Tokenizer | 4.2 MB | 61a7b147390c |
| tokenizer_config.json | Tokenizer | 518 B | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 1.8 GB
Released by Herish Kondeti through its official repository on Hugging Face. Read the license.
Built From
- Derived from google/gemma-2-2b-it
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Rainbow-AI-Specialist-MLC
Can I use Rainbow-AI-Specialist-MLC commercially?
Yes. Rainbow-AI-Specialist-MLC is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.