|
--- |
|
license: apache-2.0 |
|
tags: |
|
- finetuned |
|
pipeline_tag: text-generation |
|
model-index: |
|
- name: deepseek-coder-1.3b-chat-and-function-calling |
|
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: 26.28 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat-and-function-calling |
|
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: 39.27 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat-and-function-calling |
|
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: 26.92 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat-and-function-calling |
|
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: 43.37 |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat-and-function-calling |
|
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: 51.7 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat-and-function-calling |
|
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: 3.41 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=AIGym/deepseek-coder-1.3b-chat-and-function-calling |
|
name: Open LLM Leaderboard |
|
--- |
|
# deepseek-coder-1.3b-chat-and-function-calling |
|
It was created by starting with the deepseek-coder-1.3b and training it on the open assistant dataset then training yhat on function calling. We have attached the wandb report in pdf form to view the training run at a glance. |
|
|
|
# Reson |
|
This model was fine tuned to allow it to work with the openai syntask and will return function when apperate. |
|
|
|
# Templete |
|
Us the following templete when interacting with the fine tuned model. |
|
|
|
# Referrals |
|
Run Pod - This is who I use to train th emodels on huggingface. If you use it we both get free crdits. - <a href="https://runpod.io?ref=kilq83n1" target="_blank" style="color: #3498db; text-decoration: none; font-weight: bold;">Visit Runpod's Website!</a> |
|
|
|
Paypal - If you want to leave a tip, it is appecaheted. - <a href="https://paypal.me/OpenSourceTraining" target="_blank" style="color: #3498db; text-decoration: none; font-weight: bold;">Visit My Paypal!</a> |
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_AIGym__deepseek-coder-1.3b-chat-and-function-calling) |
|
|
|
| Metric |Value| |
|
|---------------------------------|----:| |
|
|Avg. |31.82| |
|
|AI2 Reasoning Challenge (25-Shot)|26.28| |
|
|HellaSwag (10-Shot) |39.27| |
|
|MMLU (5-Shot) |26.92| |
|
|TruthfulQA (0-shot) |43.37| |
|
|Winogrande (5-shot) |51.70| |
|
|GSM8k (5-shot) | 3.41| |
|
|
|
|
