Edit model card


  • 8x A6000s
  • Forked version of unsloth for efficient training
  • Sequence Length: 4096
  • Effective batch size: 128
  • Learning Rate: 2e-5 with linear decay
  • Epochs: 1
  • Base model trained with QLoRA (rank 64, alpha 16) and MoE adapters/routers trained in bf16
  • Num Experts: 16
  • Top K: 4
  • Adapter Dim: 512

Prompt Format



from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("serpdotai/sparsetral-16x7B-v2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("serpdotai/sparsetral-16x7B-v2", device_map="auto", trust_remote_code=True).eval()

system_str = "<|im_start|>system\n{message}<|im_end|>\n"
user_str = "<|im_start|>user\n{message}<|im_end|>\n"
assistant_str = "<|im_start|>assistant\n{message}<|im_end|>\n"

def construct_prompt(messages):
    prompt = ""
    for message in messages:
        if message["from"] in ["human", "user"]:
            prompt += user_str.format(
        elif message["from"] in ["gpt", "assistant"]:
            prompt += assistant_str.format(
        elif message["from"] in ["system", "instruction"]:
            prompt += system_str.format(
            raise ValueError(
                f"Unknown message type: {message['from']}"
    return prompt + "<|im_start|>assistant\n"

system = "You are a helpful assistant who will help the user to the best of their ability. If you don't know something, say \"I don't know\""
user = "Are you sentient?"

messages = [
    {"from": "system", "value": system},
    {"from": "user", "value": user},

prompt = construct_prompt(messages)
inputs = tokenizer(prompt, return_tensors="pt")
inputs = inputs.to(model.device)
pred = model.generate(**inputs, max_length=4096, do_sample=True, top_k=50, top_p=0.99, temperature=0.9, num_return_sequences=1)
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))

Other Information

Paper reference: Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

Original Paper repo

Forked repo with mistral support (sparsetral)

If you are interested in faster inferencing, check out our fork of vLLM that adds sparsetral support

Downloads last month

Dataset used to train LoneStriker/sparsetral-16x7B-v2-8.0bpw-h8-exl2