---
language:
- en
library_name: transformers
pipeline_tag: text-generation
datasets:
- jondurbin/airoboros-2.2
- Open-Orca/OpenOrca
- garage-bAInd/Open-Platypus
- WizardLM/WizardLM_evol_instruct_V2_196k
- TokenBender/python_eval_instruct_51k
- codefuse-ai/Evol-Instruction-66k
tags:
- llama-2
- code
license: llama2
model-index:
- name: SpeechlessCoder
  results:
  - task:
      type: text-generation
    dataset:
      type: openai_humaneval
      name: HumanEval
    metrics:
    - name: pass@1
      type: pass@1
      value: 
      verified: false
---

<p><h1> speechless-sparsetral-16x7b-MoE  </h1></p>

speechless-sparsetral-16x7b-MoE is the MoE upgraded version of [speechless-code-mistral-7b-v1.0](https://huggingface.co/uukuguy/speechless-code-mistral-7b-v1.0). The MoE fine-tuning adopts [Parameter-Efficient Sparsity Crafting (PESC)](https://arxiv.org/abs/2401.02731), which is an efficient fine-tuning architecture that uses LoRA modules as expert models, similar to the concept of [multi-loras](https://github.com/uukuguy/multi_loras). The model size is approximately **10B**. 

Specifically, Mistral-7B-0.1 is used as the base model, with 16 experts and 4 expert outputs selected for inference. The fine-tuning dataset includes codefuse-ai/Evol-Instruction-66k to enhance the model's code generation ability. The specific datasets are as follows:

- jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 23,462 samples.
- Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset. 74,440 samples.
- garage-bAInd/Open-Platypus: 100%, 24,926 samples.
- WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,185 samples
- TokenBender/python_eval_instruct_51k: “python” in output .40,309 samples
- Spider: 8,659 samples
- codefuse-ai/Evol-Instruction-66k: 100%, 66,862 samples

## Alpaca Prompt Format

```
### Instruction:
<instruction>
### Response:
```

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name_or_path="uukuguy/speechless-sparsetral-16x7b-MoE"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, device_map="auto", trust_remote_code=True).eval()

system = ""Below is an instruction that describes a task.\nWrite a response that appropriately completes the request.\n\n""
prompt = f"{system}\n\n### Instruction:\n{instruction}\n\n### Response:"

inputs = tokenizer(prompt, return_tensors="pt").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))
```