license: apache-2.0
base_model: Qwen/Qwen2-1.5B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
datasets:
- Replete-AI/code_bagel_hermes-2.5
- Replete-AI/code_bagel
- Replete-AI/OpenHermes-2.5-Uncensored
- teknium/OpenHermes-2.5
- layoric/tiny-codes-alpaca
- glaiveai/glaive-code-assistant-v3
- ajibawa-2023/Code-290k-ShareGPT
- TIGER-Lab/MathInstruct
- chargoddard/commitpack-ft-instruct-rated
- iamturun/code_instructions_120k_alpaca
- ise-uiuc/Magicoder-Evol-Instruct-110K
- cognitivecomputations/dolphin-coder
- nickrosh/Evol-Instruct-Code-80k-v1
- coseal/CodeUltraFeedback_binarized
- glaiveai/glaive-function-calling-v2
- CyberNative/Code_Vulnerability_Security_DPO
- jondurbin/airoboros-2.2
- camel-ai
- lmsys/lmsys-chat-1m
- CollectiveCognition/chats-data-2023-09-22
- CoT-Alpaca-GPT4
- WizardLM/WizardLM_evol_instruct_70k
- WizardLM/WizardLM_evol_instruct_V2_196k
- teknium/GPT4-LLM-Cleaned
- GPTeacher
- OpenGPT
- meta-math/MetaMathQA
- Open-Orca/SlimOrca
- garage-bAInd/Open-Platypus
- anon8231489123/ShareGPT_Vicuna_unfiltered
- Unnatural-Instructions-GPT4
model-index:
- name: Replete-Coder-llama3-8b
results:
- task:
name: HumanEval
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1
type: pass@1
value: 0.32926829268292684
verified: false
- task:
name: AI2 Reasoning Challenge
type: text-generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: accuracy
value: null
name: normalized accuracy
source:
url: https://www.placeholderurl.com
name: Open LLM Leaderboard
- task:
name: Text Generation
type: text-generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: accuracy
value: null
name: normalized accuracy
source:
url: https://www.placeholderurl.com
name: Open LLM Leaderboard
- task:
name: Text Generation
type: text-generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: accuracy
value: null
name: accuracy
source:
url: https://www.placeholderurl.com
name: Open LLM Leaderboard
- task:
name: Text Generation
type: text-generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: multiple_choice_accuracy
value: null
source:
url: https://www.placeholderurl.com
name: Open LLM Leaderboard
- task:
name: Text Generation
type: text-generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: accuracy
value: null
name: accuracy
source:
url: https://www.placeholderurl.com
name: Open LLM Leaderboard
- task:
name: Text Generation
type: text-generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: accuracy
value: null
name: accuracy
source:
url: https://www.placeholderurl.com
name: Open LLM Leaderboard
This is the Qwen/Qwen2-1.5B-Instruct model with the Replete-AI/Adapter_For_Replete-Coder-Qwen2-1.5b applied on top of it.
This is mostly an experinment to see how the model would perform.
Links to the oringal model and adapter are bellow:
Orginal model:
Adapter:
Original model card for Replete-Coder-Qwen2-1.5b bellow
Replete-Coder-Qwen2-1.5b
Finetuned by: Rombodawg
More than just a coding model!
Although Replete-Coder has amazing coding capabilities, its trained on vaste amount of non-coding data, fully cleaned and uncensored. Dont just use it for coding, use it for all your needs! We are truly trying to make the GPT killer!
Thank you to TensorDock for sponsoring Replete-Coder-llama3-8b and Replete-Coder-Qwen2-1.5b you can check out their website for cloud compute rental bellow.
Replete-Coder-Qwen2-1.5b is a general purpose model that is specially trained in coding in over 100 coding languages. The data used to train the model contains 25% non-code instruction data and 75% coding instruction data totaling up to 3.9 million lines, roughly 1 billion tokens, or 7.27gb of instruct data. The data used to train this model was 100% uncensored, then fully deduplicated, before training happened.
The Replete-Coder models (including Replete-Coder-llama3-8b and Replete-Coder-Qwen2-1.5b) feature the following:
- Advanced coding capabilities in over 100 coding languages
- Advanced code translation (between languages)
- Security and vulnerability prevention related coding capabilities
- General purpose use
- Uncensored use
- Function calling
- Advanced math use
- Use on low end (8b) and mobile (1.5b) platforms
Notice: Replete-Coder series of models are fine-tuned on a context window of 8192 tokens. Performance past this context window is not guaranteed.
You can find the 25% non-coding instruction below:
And the 75% coding specific instruction data below:
These two datasets were combined to create the final dataset for training, which is linked below:
Prompt Template: ChatML
<|im_start|>system
{}<|im_end|>
<|im_start|>user
{}<|im_end|>
<|im_start|>assistant
{}
Note: The system prompt varies in training data, but the most commonly used one is:
Below is an instruction that describes a task, Write a response that appropriately completes the request.
End token:
<|endoftext|>
Thank you to the community for your contributions to the Replete-AI/code_bagel_hermes-2.5 dataset. Without the participation of so many members making their datasets free and open source for any to use, this amazing AI model wouldn't be possible.
Extra special thanks to Teknium for the Open-Hermes-2.5 dataset and jondurbin for the bagel dataset and the naming idea for the code_bagel series of datasets. You can find both of their huggingface accounts linked below:
Another special thanks to unsloth for being the main method of training for Replete-Coder. Bellow you can find their github, as well as the special Replete-Ai secret sause (Unsloth + Qlora + Galore) colab code document that was used to train this model.
- https://github.com/unslothai/unsloth
- https://colab.research.google.com/drive/1eXGqy5M--0yW4u0uRnmNgBka-tDk2Li0?usp=sharing
Join the Replete-Ai discord! We are a great and Loving community!
Original model card for Qwen/Qwen2-1.5B-Instruct bellow
Qwen2-1.5B-Instruct
Introduction
Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 1.5B Qwen2 model.
Compared with the state-of-the-art opensource language models, including the previous released Qwen1.5, Qwen2 has generally surpassed most opensource models and demonstrated competitiveness against proprietary models across a series of benchmarks targeting for language understanding, language generation, multilingual capability, coding, mathematics, reasoning, etc.
For more details, please refer to our blog, GitHub, and Documentation.
Model Details
Qwen2 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes.
Training details
We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.
Requirements
The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install transformers>=4.37.0, or you might encounter the following error:
KeyError: 'qwen2'
Quickstart
Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen2-1.5B-Instruct",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-1.5B-Instruct")
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)
generated_ids = model.generate(
model_inputs.input_ids,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
Evaluation
We briefly compare Qwen2-1.5B-Instruct with Qwen1.5-1.8B-Chat. The results are as follows:
| Datasets | Qwen1.5-0.5B-Chat | Qwen2-0.5B-Instruct | Qwen1.5-1.8B-Chat | **
Qwen2-1.5B-Instruct** | | :--- | :---: | :---: | :---: | :---: | | MMLU | 35.0 | 37.9 | 43.7 | 52.4 | | HumanEval | 9.1 | 17.1 | 25.0 | 37.8 | | GSM8K | 11.3 | 40.1 | 35.3 | 61.6 | | C-Eval | 37.2 | 45.2 | 55.3 | 63.8 | | IFEval (Prompt Strict-Acc.) | 14.6 | 20.0 | 16.8 | 29.0 |
Citation
If you find our work helpful, feel free to give us a cite.
@article{qwen2,
title={Qwen2 Technical Report},
year={2024}
}