language:
- en
license: bigscience-openrail-m
library_name: transformers
tags:
- code
datasets:
- tyson0420/stackexchange-4dpo-filby-clang-keywords
metrics:
- code_eval
model-index:
- name: stack_codellama-7b-inst
results:
- 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: 43.52
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
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: 66.17
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
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: 39.59
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
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: 39.03
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
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: 65.67
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
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: 15.85
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=tyson0420/stack_codellama-7b-inst
name: Open LLM Leaderboard
Model Card for Model ID
Model Details
Evaluating generations... { "humaneval": { "pass@1": 0.32499999999999996, "pass@10": 0.4329268292682927 }, "config": { "prefix": "", "do_sample": true, "temperature": 0.2, "top_k": 0, "top_p": 0.95, "n_samples": 10, "eos": "<|endoftext|>", "seed": 0, "model": "tyson0420/stack_codellama-7b-inst", "modeltype": "causal", "peft_model": null, "revision": null, "use_auth_token": false, "trust_remote_code": false, "tasks": "humaneval", "instruction_tokens": null, "batch_size": 10, "max_length_generation": 512, "precision": "fp32", "load_in_8bit": false, "load_in_4bit": false, "left_padding": false, "limit": null, "limit_start": 0, "save_every_k_tasks": -1, "postprocess": true, "allow_code_execution": true, "generation_only": false, "load_generations_path": null, "load_data_path": null, "metric_output_path": "evaluation_results.json", "save_generations": false, "load_generations_intermediate_paths": null, "save_generations_path": "generations.json", "save_references": false, "save_references_path": "references.json", "prompt": "prompt", "max_memory_per_gpu": null, "check_references": false } }
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Developed by: [tyson0420]
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 44.97 |
| AI2 Reasoning Challenge (25-Shot) | 43.52 |
| HellaSwag (10-Shot) | 66.17 |
| MMLU (5-Shot) | 39.59 |
| TruthfulQA (0-shot) | 39.03 |
| Winogrande (5-shot) | 65.67 |
| GSM8k (5-shot) | 15.85 |