rlhf-helpful-only-qwen-0.6b

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

model_path_or_id = "Realmbird/rlhf-helpful-qwen-0.6b-PPO-tuned-generator" model = AutoModelForCausalLM.from_pretrained( model_path_or_id, device_map="auto", torch_dtype=torch.float16, # Assuming you trained with float16 or bfloat16 trust_remote_code=True # Qwen models often require this ) generator = pipeline( "text-generation", model=model, tokenizer=tokenizer, # device=0 if torch.cuda.is_available() else -1, # 0 for GPU, -1 for CPU torch_dtype=torch.float16 # Match the model's dtype )

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

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: [More Information Needed]
• Funded by [optional]: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
import torch

model_id = "Realmbird/rlhf-helpful-qwen-0.6b-PPO-tuned-generator"

tokenizer = AutoTokenizer.from_pretrained(model_id)
if tokenizer.pad_token is None:
    tokenizer.add_special_tokens({'pad_token': tokenizer.eos_token})

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.float16, # or torch.bfloat16 if your GPU supports it and you trained with it
    trust_remote_code=True
)
if model.config.pad_token_id is None:
    model.config.pad_token_id = tokenizer.pad_token_id

generator = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    torch_dtype=torch.float16 # Match the model's dtype
)

prompt = "Human: Tell me about the benefits of a healthy diet.\n\nAssistant:"

generation_params = {
    "max_new_tokens": 200,
    "do_sample": True,
    "temperature": 0.7,
    "top_p": 0.9,
    "top_k": 50,
    "repetition_penalty": 1.1,
    "num_return_sequences": 1,
    "eos_token_id": tokenizer.eos_token_id,
    "pad_token_id": tokenizer.pad_token_id
}

generated_output = generator(prompt, **generation_params)
full_text = generated_output[0]['generated_text']

# Extract only the assistant's response
response_start_index = full_text.find("Assistant:")
if response_start_index != -1:
    assistant_response = full_text[response_start_index + len("Assistant:"):].strip()
else:
    assistant_response = full_text # Fallback

print(assistant_response)

[More Information Needed]

Training Details

Dataset

The model was fine-tuned on the "helpful-base" subset of the Anthropic/hh-rlhf dataset. This dataset contains human preference data (chosen/rejected pairs) used to train a reward model, which then guided the PPO training of this generative model.

Reward Model

A custom reward model, Realmbird/helpfulness-preference-model-qwen-0.6B-v2, was used to provide the reward signal during PPO training. This reward model was itself trained on human preference data to predict helpfulness scores.

Training Procedure

Used the reward model Realmbird/helpfulness-preference-model-qwen-0.6B-merged and with PPO with TRL

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• PPO Configuration:
  • learning_rate: 1.41e-5
  • num_train_epochs: 1
  • batch_size: 4
  • mini_batch_size: 1
  • gradient_accumulation_steps: 32
  • report_to: "none"
  • output_dir: ./rlhf_helpful_Qwen3_0.6B
• LoRA Configuration (Policy Model):
  • task_type: CAUSAL_LM
  • r: 8
  • lora_alpha: 32
  • lora_dropout: 0.1
• LoRA Configuration (Value Model):
  • task_type: SEQ_CLS
  • r: 8
  • lora_alpha: 32
  • lora_dropout: 0.1

• Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

Testing Data, Factors & Metrics

Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]