metadata

language:
  - en
license: llama2
library_name: transformers
tags:
  - llama-2
  - code
datasets:
  - jondurbin/airoboros-2.2
  - Open-Orca/OpenOrca
  - garage-bAInd/Open-Platypus
  - WizardLM/WizardLM_evol_instruct_V2_196k
  - TokenBender/python_eval_instruct_51k
pipeline_tag: text-generation
model-index:
  - name: SpeechlessCoder
    results:
      - task:
          type: text-generation
        dataset:
          name: HumanEval
          type: openai_humaneval
        metrics:
          - type: pass@1
            value: 52.439
            name: pass@1
            verified: false
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 41.21
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-coding-7b-16k-tora
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 64.45
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-coding-7b-16k-tora
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 39.14
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-coding-7b-16k-tora
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 44.91
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-coding-7b-16k-tora
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 63.61
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-coding-7b-16k-tora
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 17.29
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=uukuguy/speechless-coding-7b-16k-tora
          name: Open LLM Leaderboard

speechless-coding-7b-16k-tora

Use the following dataset to fine-tune llm_agents/tora-code-7b-v1.0 in order to improve the model's reasoning and planning abilities.

context window length: 16,384 prompt_type = "alpaca" max_tokens > 128 && < 16384

Total 177,333 samples 316 MB

jondurbin/airoboros-2.2: Filter categories related to coding, reasoning and planning. 21,923 samples.
Open-Orca/OpenOrca: Filter the 'cot' category in 1M GPT4 dataset. 62,973 samples.
garage-bAInd/Open-Platypus: 100%, 22,760 samples.
WizardLM/WizardLM_evol_instruct_V2_196k: Coding coversation part. 30,081 samples
TokenBender/python_eval_instruct_51k: “python” in output .39,596 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	52.44

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

MultiPL-E

Metric	Value
python	55.96
java	37.84
javascript	46.93
cpp	37.48
rust	29.01
go	28.99
sh	12.11
julia	31.47
typescript	47.80

LMEval

Open LLM Leaderboard

Metric	Value
ARC
HellaSwag
MMLU
TruthfulQA
Average

Parameters


lr	2e-4
lr_scheduler_type	cosine
weight_decay	0.0
optim	paged_adamw_8bit
flash_attention	True
rerope	False
max_new_tokens	16384
num_train_epochs	2
bits	4
lora_r	64
lora_alpha	256
lora_dropout	0.05
double_quant	True
quant_type	nf4
dataset_format	sharegpt
mini_batch_size	2
grandient_accumulation_steps	32
bf16	True

A100-40G x 4

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	45.10
AI2 Reasoning Challenge (25-Shot)	41.21
HellaSwag (10-Shot)	64.45
MMLU (5-Shot)	39.14
TruthfulQA (0-shot)	44.91
Winogrande (5-shot)	63.61
GSM8k (5-shot)	17.29