GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
dwivedula
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
dwivedula
Model Tree
unsloth/Qwen2.5-7B-Instruct-bnb-4bit
Input Modalities
Output Modalities
Supported Functionality
Samrudh-1 (7B) is a sovereign, post-trained instruction-tuned reasoning model engineered and released by Samrudh (dwivedula).
Trained on an Apache 2.0 foundation using high-efficiency 4-bit NormalFloat4 (NF4) QLoRA, Samrudh-1 was specifically post-trained to serve as the core cognitive brain for an upcoming sovereign autonomous intelligence operating system. It bridges high-precision enterprise compliance, quantitative financial risk models, biomedical pharmacology, and authentic regional Indic dialects.
Unlike models that produce stilted, machine-translated Telugu, Samrudh-1 natively captures cultural cadence, humor, and syntactic precision across regional linguistic registers:
Most LLMs suffer from severe attention degradation across long documents (the U-shaped attention curve). Samrudh-1 was trained using bidirectional prompt sandwiching and strict verbatim quote grounding:
Native comprehension and audit capabilities against dangerous contractual clauses:
| Parameter | Specification |
|---|---|
| Base Architecture | Qwen 2.5 7B Instruct (Apache 2.0) |
| Quantization | 4-bit NormalFloat4 (NF4) with Double Quantization |
| LoRA Rank (r) | 16 |
| LoRA Alpha (alpha) | 32 |
| Target Projections | All linear attention matrices (q, k, , , , , ) |
transformers)python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "dwivedula/Samrudh-1-Brahma-7B" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, device_map="auto") prompt = """Below is an instruction that describes a task. Write a response that appropriately completes the request. ### Instruction:Who are you and what makes your reasoning architecture sovereign? ### Response:""" inputs = tokenizer(prompt, return_tensors="pt").to("cuda")outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)print(tokenizer.decode(outputs[0], skip_special_tokens=True))Run directly on your local machine (even on laptops without a dedicated GPU):
bash
# Pull and run the 4-bit quantized model directly from Hugging Faceollama run hf.co/dwivedula/Samrudh-1-Brahma-7B-GGUFOr using the local GGUF file:
bash
# 1. Download Qwen2.5-7B-Instruct.Q4_K_M.gguf and Modelfile# 2. Build and launch:ollama create samrudh-1 -f Modelfileollama run samrudh-1Evaluated across varying context depths (Start 10%, Middle 50%, End 90%):
| Document Length | Start (Primacy) | Middle (U-Curve Valley) | End (Recency) | Overall Accuracy |
|---|---|---|---|---|
| 1,500 Tokens | 100% | 100% | 100% | 100.0% |
| 4,000 Tokens | 100% | 100% | 100% | 100.0% |
| 8,000 Tokens | 100% | 100% | 100% |
Evaluation methodology: Exact verbatim quote extraction from multi-document distractors.
This model is post-trained and released by Samrudh (dwivedula) under the Apache License 2.0.
dwivedula)vogateupdown| Hardware Used | 1x Tesla T4 GPU (15GB VRAM) on Google Colab |
| Peak VRAM Consumption | <6.8 GB VRAM (Zero OOM) |
| Optimizer | Paged 8-bit AdamW |
| Context Window | 2,048 (Train) / Up to 32,768 (Inference via RoPE) |
| License | Apache License 2.0 (100% Royalty-Free & Commercial) |
| 100.0% |