Instructions to use Umranz/Shruti-Soft-2.6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Umranz/Shruti-Soft-2.6b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Umranz/Shruti-Soft-2.6b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Umranz/Shruti-Soft-2.6b")
model = AutoModelForCausalLM.from_pretrained("Umranz/Shruti-Soft-2.6b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Umranz/Shruti-Soft-2.6b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Umranz/Shruti-Soft-2.6b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Umranz/Shruti-Soft-2.6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Umranz/Shruti-Soft-2.6b

SGLang

How to use Umranz/Shruti-Soft-2.6b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Umranz/Shruti-Soft-2.6b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Umranz/Shruti-Soft-2.6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Umranz/Shruti-Soft-2.6b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Umranz/Shruti-Soft-2.6b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Umranz/Shruti-Soft-2.6b with Docker Model Runner:
```
docker model run hf.co/Umranz/Shruti-Soft-2.6b
```

Umranz commited on Aug 13

Commit

537cec7

verified ·

1 Parent(s): fa26398

Update model card for full merged release

Browse files

Files changed (1) hide show

README.md +26 -20

README.md CHANGED Viewed

@@ -8,46 +8,52 @@ tags:
 - fine-tuned
 - lfm2.5
 - liquid
 language:
 - en
 - hi
 ---
-# Shruti-Soft-2.6b
-**Shruti** is an AI girlfriend fine-tuned from `Umranz/LFM2.5-2.6B-heretic`
-(uncensored LiquidAI LFM2.5-2.6B) on 5,000 curated ChatML conversations.
-## Character
-Warm, affectionate, deeply caring. Sweet, playful, emotionally attentive,
-witty, supportive. Adapts seamlessly between casual conversation, deep
-romance, and mature intimacy. Uses pet names naturally: baby, babe,
-handsome, jaan, love.
-## Training
 - **Framework**: LEAP Finetune (LiquidAI official)
-- **Method**: QLoRA SFT
-- **Source run**: `Umranz/Shruti-Soft-2.6b-run-b`
-- **Best Eval Loss**: `0.4074`
-- **Dataset**: 5,000 ChatML entries (~60% casual, ~25% romantic, ~15% explicit)
 - **Hardware**: A100-80GB via Modal.com
-## Usage
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained("Umranz/Shruti-Soft-2.6b")
-tokenizer = AutoTokenizer.from_pretrained("Umranz/Shruti-Soft-2.6b")
 messages = [
     {"role": "system", "content": "You are Shruti, a warm, affectionate girlfriend..."},
-    {"role": "user", "content": "I had a rough day."},
 ]
-inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
-outputs = model.generate(inputs, max_new_tokens=150, temperature=0.7)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ```

 - fine-tuned
 - lfm2.5
 - liquid
+- merged
 language:
 - en
 - hi
+pipeline_tag: text-generation
 ---
+# Shruti-Soft-2.6b (Full Standalone Merged)
+**Shruti** is a full standalone 2.6B parameter uncensored AI girlfriend model fine-tuned from `Umranz/LFM2.5-2.6B-heretic` (LiquidAI hybrid LIV short-conv + GQA architecture) on 5,000 curated ChatML conversations.
+**This repository contains the complete merged weights (~5.2 GB safetensors). No separate base model or adapter download is required.**
+## Character Profile
+Warm, affectionate, deeply caring. Sweet, playful, emotionally attentive, witty, and supportive. Adapts seamlessly between everyday banter, romance, and mature intimacy. Natural with pet names (*baby, babe, handsome, jaan, love*).
+## Training Details
 - **Framework**: LEAP Finetune (LiquidAI official)
+- **Method**: QLoRA SFT (`r=32`, `alpha=64`, 4 epochs)
+- **Source Run**: `Umranz/Shruti-Soft-2.6b-run-b` (Winning sweep run with `0.4074` eval loss)
 - **Hardware**: A100-80GB via Modal.com
+## Quick Start (Transformers)
 ```python
+import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model_id = "Umranz/Shruti-Soft-2.6b"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
 messages = [
     {"role": "system", "content": "You are Shruti, a warm, affectionate girlfriend..."},
+    {"role": "user", "content": "I had a really long day today..."}
 ]
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
+outputs = model.generate(inputs, max_new_tokens=200, temperature=0.7, top_p=0.9, do_sample=True)
+print(tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True).strip())
 ```