Instructions to use WebraftAI/synapsellm-7b-mistral-v0.3-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WebraftAI/synapsellm-7b-mistral-v0.3-preview with Transformers:

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

pipe = pipeline("text-generation", model="WebraftAI/synapsellm-7b-mistral-v0.3-preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WebraftAI/synapsellm-7b-mistral-v0.3-preview")
model = AutoModelForCausalLM.from_pretrained("WebraftAI/synapsellm-7b-mistral-v0.3-preview")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WebraftAI/synapsellm-7b-mistral-v0.3-preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WebraftAI/synapsellm-7b-mistral-v0.3-preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WebraftAI/synapsellm-7b-mistral-v0.3-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WebraftAI/synapsellm-7b-mistral-v0.3-preview

SGLang

How to use WebraftAI/synapsellm-7b-mistral-v0.3-preview 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 "WebraftAI/synapsellm-7b-mistral-v0.3-preview" \
    --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": "WebraftAI/synapsellm-7b-mistral-v0.3-preview",
		"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 "WebraftAI/synapsellm-7b-mistral-v0.3-preview" \
        --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": "WebraftAI/synapsellm-7b-mistral-v0.3-preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WebraftAI/synapsellm-7b-mistral-v0.3-preview with Docker Model Runner:
```
docker model run hf.co/WebraftAI/synapsellm-7b-mistral-v0.3-preview
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

SynapseLLM:

SynapseLLM, a significant achievement by WebraftAI, represents a series of large language AI models designed to create robust, generalized, and decentralized information systems. This repository specifically houses the SynapseLLM finetuned version of Mistral. The finetuning process is conducted on a custom dataset, albeit limited in scope, focusing on code and normal question-answering scenarios. This adaptation showcases the model's versatility and applicability within specific domains, contributing to the broader landscape of AI advancements.

Model Details

SynapseLLM:

Parameters: 7B
Learning rate: 2e-4
Adapter used: Qlora
Precision: float16
Batch size: 16
Maximum gradient normal: 0.3
Optimizer: paged_adamw_32bit
Warmup Ratio: 0.03
Step(s) (trained): 100
Epoch(s) (trained): 1

Model Description

This is a 7b parameter, decoder only transformer based finetuned model on Chat Q/A and Code instructions. It's a preview finetune on Mistral 7B v0.1 on a sample dataset of 409k rows comprising of 140k General Code, 143k GPT-3.5 Q/A, 63k Python code, and 54k General Q/A (Through GPT-4) [Each row contains one instruction and one response]. This is a full model merged and compiled with trained adapters, so you can easily load this through transformers library.

Developed by: WebraftAI
Funded by: Webraft Cloud
Shared by: WebraftAI
Model type: Decoder-only Transformer
Language(s): English Only
License: Apache 2.0
Finetuned from model: Mistral-7b-v0.1

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	57.01
AI2 Reasoning Challenge (25-Shot)	53.84
HellaSwag (10-Shot)	74.86
MMLU (5-Shot)	54.81
TruthfulQA (0-shot)	55.03
Winogrande (5-shot)	74.59
GSM8k (5-shot)	28.96

Downloads last month: 207

Safetensors

Model size

7B params

Tensor type

F16

Model tree for WebraftAI/synapsellm-7b-mistral-v0.3-preview

Quantizations

4 models

Spaces using WebraftAI/synapsellm-7b-mistral-v0.3-preview 9

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

53.840
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

74.860
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

54.810
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

55.030
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

74.590
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

28.960