speechless-code-mistral-7b-v1.0

• AWQ model(s) for GPU inference.
• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference

Code: https://github.com/uukuguy/speechless

Use the following dataset to fine-tune mistralai/Mistral-7B-v0.1 in order to improve the model's reasoning and planning abilities.

Total 201,981 samples.

• 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

How to Prompt the Model

This model accepts the Alpaca instruction format.

For example:

You are an intelligent programming assistant.

### Instruction:
Implement a linked list in C++

### Response:

HumanEval

Big Code Evaluation

Big Code Models Leaderboard

CodeLlama-34B-Python: 53.29

CodeLlama-34B-Instruct: 50.79

CodeLlama-13B-Instruct: 50.6

CodeLlama-34B: 45.11

CodeLlama-13B-Python: 42.89

CodeLlama-13B: 35.07

lm-evaluation-harness

{'ARC (acc_norm)': 0.6109215017064846,
'HellaSwag (acc_norm)': 0.8358892650866361,
'MMLU (acc)': 0.6325456394049195,
'TruthfulQA (mc2)': 0.4746745250371087,
'Winoground (acc)': 0.7829518547750592,
'GSM8K (acc)': 0.467778620166793,
'DROP (f1)': 0.49585675335570545,
'Open LLM Score': 0.61437428571428571}

Open LLM Leaderboard

Parameters

A40-48G x 2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here