Instructions to use solvrays/solvrays-llm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solvrays/solvrays-llm with Transformers:

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

pipe = pipeline("text-generation", model="solvrays/solvrays-llm")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solvrays/solvrays-llm")
model = AutoModelForCausalLM.from_pretrained("solvrays/solvrays-llm", 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 solvrays/solvrays-llm with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/solvrays/solvrays-llm

SGLang

How to use solvrays/solvrays-llm 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 "solvrays/solvrays-llm" \
    --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": "solvrays/solvrays-llm",
		"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 "solvrays/solvrays-llm" \
        --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": "solvrays/solvrays-llm",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use solvrays/solvrays-llm with Docker Model Runner:
```
docker model run hf.co/solvrays/solvrays-llm
```

singtan commited on Apr 30

Commit

8bdabf8

verified ·

1 Parent(s): 5a13b18

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +56 -24

README.md CHANGED Viewed

@@ -5,36 +5,68 @@ library_name: transformers
 license: apache-2.0
 pipeline_tag: text-generation
 tags:
-- fine-tuned
-- pdf-grounded
 - zero-hallucination
-- precise-retrieval
 ---
-# 📂 Solvrays Llm (Ground-Truth Precise)
-            ## 🌟 Overview
-            This is a specialized fine-tuned version of **Gemma 2B**, optimized for **High-Precision Retrieval**. It uses deterministic grounding templates to minimize hallucinations.
-            ## 💻 Quick Start (Inference)
-            ```python
-            from transformers import AutoTokenizer, AutoModelForCausalLM
-            import torch
-            model_id = "solvrays/solvrays-llm"
-            tokenizer = AutoTokenizer.from_pretrained(model_id)
-            model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)
-            instruction = "Analyze the following document and provide a precise, factual response based strictly on the content provided."
-            prompt = f"### Instruction: {instruction}
-### Source: Document.pdf
-### Content: Query
-### Verified Response:"
-            inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-            outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False)
-            print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-            ```
-            ---
-            **Fine-tuned by Bibek Lama Singtan**

 license: apache-2.0
 pipeline_tag: text-generation
 tags:
+- precision-grounding
+- document-qa
 - zero-hallucination
+- legal-tech
+- technical-analysis
 ---
+# 📂 Solvrays Llm - High Precision Document Analyst
+## 🌟 Overview
+This model is a specialized fine-tuning of **google/gemma-2b**, engineered for **Zero-Hallucination Document Retrieval**. It has been optimized to handle complex, domain-specific documents (Technical, Legal, or Architectural) with strict adherence to provided context.
+### 🛠 Primary Design Objectives
+- **Factual Integrity**: Programmed to prioritize 'Not Documented' over speculating.
+- **Contextual Continuity**: Overlap-aware training prevents information loss across page boundaries.
+- **Domain Versatility**: Seamlessly switches between technical and non-technical document styles.
+## 💻 Professional Usage (Grounded Inference)
+To achieve the trained precision level, utilize the following code implementation:
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+model_id = 'solvrays/solvrays-llm'
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map='auto', torch_dtype=torch.float16)
+# Universal Grounding Template
+instruction = 'Analyze the document and provide a precise response based strictly on the content provided.'
+source_doc = 'Architecture_Spec.pdf'
+query = 'What are the main infrastructure requirements?'
+prompt = (f'### Instruction: {instruction}
+'
+          f'### Source: {source_doc}
+'
+          f'### Content: {query}
+'
+          f'### Verified Response:')
+inputs = tokenizer(prompt, return_tensors='pt').to(model.device)
+with torch.no_grad():
+    outputs = model.generate(**inputs, max_new_tokens=256, do_sample=False, repetition_penalty=1.5)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True).split('### Verified Response:')[-1].strip())
+```
+## 📊 Technical Specifications
+| Parameter | Configuration |
+| :--- | :--- |
+| Base Model | google/gemma-2b |
+| Fine-tuning Method | QLoRA (4-bit quantization) |
+| LoRA Rank (r) | 16 |
+| LoRA Alpha | 32 |
+| Training Epochs | 5 |
+| Context Strategy | 512 tokens with 128-token overlap |
+## ⚠️ Risks & Limitations
+- **Context Window**: Strictly limited to the fine-tuned block size (512 tokens). For longer multi-page queries, RAG (Retrieval Augmented Generation) is recommended.
+- **Bias**: The model reflects the biases of the provided training documentation.
+- **Accuracy**: Always verify critical technical numbers against the original source.
+---
+**Architected and Fine-tuned by Bibek Lama Singtan**