speechless-coder-ds-6.7b

4, 5 and 8-bit GGUF models for CPU+GPU inference

Use the following dataset to fine-tune deepseek-ai/deepseek-coder-6.7b in order to improve the model's reasoning and planning abilities.

context window length: 8192 max_tokens > 128 && < 8192

Total 185,193 samples 426 MB

• ise-uiuc/Magicoder-OSS-Instruct-75K 75,186 samples
• ise-uiuc/Magicoder-Evol-Instruct-110K 110,007 samples

50 samples/T=0.2/MaxTokens=512/Top_P=0.95

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

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

Metric	Value
humaneval-python

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

BigCode Eval

0.314188

• metrics_humanevalfixtests-cpp: "pass@1": 0.27439024390243905
• metrics_humanevalfixtests-go: "pass@1": 0.23170731707317074
• metrics_humanevalfixtests-java: "pass@1": 0.25609756097560976
• metrics_humanevalfixtests-js: "pass@1": 0.21951219512195122
• metrics_humanevalfixtests-python: "pass@1": 0.23780487804878048
• metrics_humanevalfixtests-rust: "pass@1": 0.13414634146341464

0.390111

• metrics_humanevalsynthesize-cpp: "pass@1": 0.3780487804878049
• metrics_humanevalsynthesize-go: "pass@1": 0.25609756097560976
• metrics_humanevalsynthesize-java: "pass@1": 0.45121951219512196
• metrics_humanevalsynthesize-js: "pass@1": 0.4268292682926829
• metrics_humanevalsynthesize-python: "pass@1": 0.5365853658536586
• metrics_humanevalsynthesize-rust: "pass@1": 0.25
• metrics_mbpp: "pass@1": 0.432

LMEval

Open LLM Leaderboard

Metric	Value
ARC
HellaSwag
MMLU
TruthfulQA
Average