LoneStriker/speechless-code-mistral-7b-v1.0-4.0bpw-h6-exl2

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

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

HumanEval

Metric	Value
humaneval-python	50.0

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

Open LLM Leaderboard

Metric	Value
ARC	59.64
HellaSwag	82.25
MMLU	61.33
TruthfulQA	48.45
Average	62.92

Parameters

lr	2e-4
lr_scheduler_type	cosine
weight_decay	0.0
optim	paged_adamw_8bit
flash_attention	True
rerope	False
max_new_tokens	4096
num_train_epochs	2
bits	4
lora_r	64
lora_alpha	16
lora_dropout	0.05
double_quant	True
quant_type	nf4
dataset_format	airoboros
mini_batch_size	2
grandient_accumulation_steps	32
bf16	True

A40-48G x 2

epoch	2.0
etrain_loss	0.5
etrain_runtime	1 day, 10:25:26.77
etrain_samples_per_second	3.194
etrain_steps_per_second	0.025
eeval_loss	0.5146
eeval_runtime	0:00:25.04
eeval_samples_per_second	7.985
eeval_steps_per_second