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")
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

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 8 days ago

Commit

5a13b18

verified ·

1 Parent(s): 5586bf7

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +17 -20

README.md CHANGED Viewed

@@ -1,17 +1,20 @@
 ---
-{}
 ---
-            # 📂 Solvrays Llm (Ground-Truth Precise)
             ## 🌟 Overview
-            This is a specialized fine-tuned version of **Gemma 2B**, optimized for **High-Precision Document Retrieval**. It has been trained using strict grounding templates to ensure zero-hallucination and deterministic factual responses.
-            ## 🛠 Key Advanced Features
-            - **Zero-Hallucination Mode**: Deterministic greedy decoding by default.
-            - **Negative Constraint Awareness**: Trained to avoid guessing when information is missing.
-            - **Domain Agnostic**: Works for any technical or non-technical PDF provided as context.
-            - **Standalone Conversion**: Fully merged FP16 weights for production deployment.
             ## 💻 Quick Start (Inference)
             ```python
@@ -22,22 +25,16 @@
             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. If the information is not present, you must state that it is not documented."
             prompt = f"### Instruction: {instruction}
-### Source: Document_Name.pdf
-### Content: Your Query Here
 ### Verified Response:"
             inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-            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())
             ```
-            ## 📊 Training methodology
-            - **Base Model**: google/gemma-2b
-            - **Quantization**: 4-bit (NormalFloat4)
-            - **LoRA Config**: r=16, alpha=32, target_modules=All linears
-            - **Epochs**: 5 (Intensive Reinforcement)
             ---
             **Fine-tuned by Bibek Lama Singtan**

 ---
+base_model: google/gemma-2b
+language: en
+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
             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**