speechless-thoughts-mistral-7b is fine-tuned as a baseline of the speechless-sparsetral-16x7b-MoE.
The specific datasets (speechless-thoughts-252k) 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
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name_or_path="uukuguy/speechless-thoughts-mistral-7b"
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))
HumanEval
| Metric | Value |
|---|---|
| humaneval-python |
lm-evaluation-harness
{'ARC (acc_norm)': ,
'HellaSwag (acc_norm)': ,
'MMLU (acc)': ,
'TruthfulQA (mc2)': ,
'Winoground (acc)': ,
'GSM8K (acc)': ,
'DROP (f1)': ,
'Open LLM Score': }
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 59.72 |
| ARC (25-shot) | 58.96 |
| HellaSwag (10-shot) | 80.71 |
| MMLU (5-shot) | 60.11 |
| TruthfulQA (0-shot) | 49.91 |
| Winogrande (5-shot) | 77.82 |
| GSM8K (5-shot) | 30.78 |